45 DBMS_DATA_MINING_TRANSFORM

Syntax

DBMS_DATA_MINING_TRANSFORM.CREATE_BIN_CAT (
     bin_table_name     IN VARCHAR2,
     bin_schema_name    IN VARCHAR2 DEFAULT NULL );

Parameters

Usage Notes

You can use the following procedures to populate the transformation definition table:

• INSERT_BIN_CAT_FREQ Procedure — frequency-based binning

• INSERT_BIN_SUPER Procedure — supervised binning

Examples

The following statement creates a table called bin_cat_xtbl in the current schema. The table has columns that can be populated with bin assignments for categorical attributes.

BEGIN
   DBMS_DATA_MINING_TRANSFORM.CREATE_BIN_CAT('bin_cat_xtbl');
END;
/
DESCRIBE bin_cat_xtbl
 Name                                      Null?    Type
 ----------------------------------------- -------- ----------------------------
 COL                                                VARCHAR2(30)
 ATT                                                VARCHAR2(4000)
 VAL                                                VARCHAR2(4000)
 BIN                                                VARCHAR2(4000)

Syntax

DBMS_DATA_MINING_TRANSFORM.CREATE_BIN_NUM (
     bin_table_name    IN VARCHAR2,
     bin_schema_name   IN VARCHAR2 DEFAULT NULL );

Parameters

Usage Notes

You can use the following procedures to populate the transformation definition table:

• INSERT_AUTOBIN_NUM_EQWIDTH Procedure — automatic equi-width binning

• INSERT_BIN_NUM_EQWIDTH Procedure — user-specified equi-width binning

• INSERT_BIN_NUM_QTILE Procedure — quantile binning

• INSERT_BIN_SUPER Procedure — supervised binning

Examples

The following statement creates a table called bin_num_xtbl in the current schema. The table has columns that can be populated with bin assignments for numerical attributes.

BEGIN
  DBMS_DATA_MINING_TRANSFORM.CREATE_BIN_NUM('bin_num_xtbl');
END;
/
 
DESCRIBE bin_num_xtbl
 Name                                      Null?    Type
 ----------------------------------------- -------- ----------------------------
 COL                                                VARCHAR2(30)
 ATT                                                VARCHAR2(4000)
 VAL                                                NUMBER
 BIN                                                VARCHAR2(4000)

Syntax

DBMS_DATA_MINING_TRANSFORM.CREATE_CLIP (
     clip_table_name    IN VARCHAR2,
     clip_schema_name   IN VARCHAR2 DEFAULT NULL );

Parameters

Usage Notes

You can use the following procedures to populate the transformation definition table:

• INSERT_CLIP_TRIM_TAIL Procedure — replaces outliers with nulls

• INSERT_CLIP_WINSOR_TAIL Procedure — replaces outliers with an average value

Examples

The following statement creates a table called clip_xtbl in the current schema. The table has columns that can be populated with clipping instructions for numerical attributes.

BEGIN
  DBMS_DATA_MINING_TRANSFORM.CREATE_CLIP('clip_xtbl');
END;
/
 
DESCRIBE clip_xtbl
 Name                                      Null?    Type
 ----------------------------------------- -------- ----------------------------
 COL                                                VARCHAR2(30)
 ATT                                                VARCHAR2(4000)
 LCUT                                               NUMBER
 LVAL                                               NUMBER
 RCUT                                               NUMBER
 RVAL                                               NUMBER

Syntax

DBMS_DATA_MINING_TRANSFORM.CREATE_COL_REM (
      rem_table_name           VARCHAR2,
      rem_schema_name          VARCHAR2 DEFAULT NULL );

Parameters

Usage Notes

See "Operational Notes".

Examples

The following statement creates a table called rem_att_xtbl in the current schema. The table has columns that can be populated with the names of attributes to exclude from the data to be mined.

BEGIN
    DBMS_DATA_MINING_TRANSFORM.CREATE_COL_REM ('rem_att_xtbl');
END;
 /
DESCRIBE rem_att_xtbl
 Name                                      Null?    Type
 ----------------------------------------- -------- ----------------------------
 COL                                                VARCHAR2(30)
 ATT                                                VARCHAR2(4000)

Syntax

DBMS_DATA_MINING_TRANSFORM.CREATE_MISS_CAT (
     miss_table_name       IN VARCHAR2,
     miss_schema_name      IN VARCHAR2 DEFAULT NULL );

Parameters

Usage Notes

You can use the INSERT_MISS_CAT_MODE Procedure to populate the transformation definition table.

Examples

The following statement creates a table called miss_cat_xtbl in the current schema. The table has columns that can be populated with values for missing data in categorical attributes.

BEGIN

  DBMS_DATA_MINING_TRANSFORM.CREATE_MISS_CAT('miss_cat_xtbl');
END;
/
 
DESCRIBE miss_cat_xtbl
 Name                                      Null?    Type
 ----------------------------------------- -------- ----------------------------
 COL                                                VARCHAR2(30)
 ATT                                                VARCHAR2(4000)
 VAL                                                VARCHAR2(4000)

Syntax

DBMS_DATA_MINING_TRANSFORM.CREATE_MISS_NUM (
     miss_table_name       IN VARCHAR2,
     miss_schema_name      IN VARCHAR2 DEFAULT NULL );

Parameters

Usage Notes

You can use the INSERT_MISS_NUM_MEAN Procedure to populate the transformation definition table.

Example

The following statement creates a table called miss_num_xtbl in the current schema. The table has columns that can be populated with values for missing data in numerical attributes.

BEGIN
    DBMS_DATA_MINING_TRANSFORM.CREATE_MISS_NUM('miss_num_xtbl');
END;
/
 
DESCRIBE miss_num_xtbl
 Name                                      Null?    Type
 ----------------------------------------- -------- ----------------------------
 COL                                                VARCHAR2(30)
 ATT                                                VARCHAR2(4000)
 VAL                                                NUMBER

Syntax

DBMS_DATA_MINING_TRANSFORM.CREATE_NORM_LIN (
     norm_table_name       IN VARCHAR2,
     norm_schema_name      IN VARCHAR2 DEFAULT NULL );

Parameters

Usage Notes

You can use the following procedures to populate the transformation definition table:

• INSERT_NORM_LIN_MINMAX Procedure — Uses linear min-max normalization

• INSERT_NORM_LIN_SCALE Procedure — Uses linear scale normalization

• INSERT_NORM_LIN_ZSCORE Procedure — Uses linear zscore normalization

Examples

The following statement creates a table called norm_xtbl in the current schema. The table has columns that can be populated with shift and scale values for normalizing numerical attributes.

BEGIN
     DBMS_DATA_MINING_TRANSFORM.CREATE_NORM_LIN('norm_xtbl');
END;
/
 
DESCRIBE norm_xtbl
 Name                                      Null?    Type
 ----------------------------------------- -------- ----------------------------
 COL                                                VARCHAR2(30)
 ATT                                                VARCHAR2(4000)
 SHIFT                                              NUMBER
 SCALE                                              NUMBER

Syntax

DBMS_DATA_MINING_TRANSFORM.DESCRIBE_STACK (
     xform_list           IN  TRANSFORM_LIST,
     data_table_name      IN  VARCHAR2,
     describe_list        OUT DESCRIBE_LIST,
     data_schema_name     IN  VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes" for information about transformation lists and embedded transformations.

Examples

This example shows the column name and data type, the column name length, and the column maximum length for the view dmuser.cust_info after the transformation list has been applied. All the transformations are user-specified. The results of DESCRIBE_STACK do not include one of the columns in the original table, because the SET_TRANSFORM procedure sets that column to NULL.

CREATE OR REPLACE VIEW cust_info AS
         SELECT a.cust_id, c.country_id, c.cust_year_of_birth,
         CAST(COLLECT(DM_Nested_Numerical(
                  b.prod_name, 1))
                AS DM_Nested_Numericals) custprods
                 FROM sh.sales a, sh.products b, sh.customers c
                  WHERE a.prod_id = b.prod_id AND
                        a.cust_id=c.cust_id and
                        a.cust_id between 100001 AND 105000
         GROUP BY a.cust_id, country_id, cust_year_of_birth;
 
describe cust_info
 Name                                      Null?    Type
 ----------------------------------------- -------- ----------------------------
 CUST_ID                                   NOT NULL NUMBER
 COUNTRY_ID                                NOT NULL NUMBER
 CUST_YEAR_OF_BIRTH                        NOT NULL NUMBER(4)
 CUSTPRODS                                          SYS.DM_NESTED_NUMERICALS
 
DECLARE
  cust_stack   dbms_data_mining_transform.TRANSFORM_LIST;
  cust_cols    dbms_data_mining_transform.DESCRIBE_LIST;
BEGIN
  dbms_data_mining_transform.SET_TRANSFORM (cust_stack,
     'country_id', NULL, 'country_id/10', 'country_id*10');
  dbms_data_mining_transform.SET_TRANSFORM (cust_stack,
      'cust_year_of_birth', NULL, NULL, NULL);
  dbms_data_mining_transform.SET_TRANSFORM (cust_stack,
      'custprods', 'Mouse Pad', 'value*100', 'value/100');
  dbms_data_mining_transform.DESCRIBE_STACK(
       xform_list => cust_stack,
       data_table_name => 'cust_info',
       describe_list => cust_cols);
  dbms_output.put_line('====');
  for i in 1..cust_cols.COUNT loop
    dbms_output.put_line('COLUMN_NAME:     '||cust_cols(i).col_name);
    dbms_output.put_line('COLUMN_TYPE:     '||cust_cols(i).col_type);
    dbms_output.put_line('COLUMN_NAME_LEN: '||cust_cols(i).col_name_len);
    dbms_output.put_line('COLUMN_MAX_LEN:  '||cust_cols(i).col_max_len);
    dbms_output.put_line('====');
  END loop;
END;
/
====
COLUMN_NAME:     CUST_ID
COLUMN_TYPE:     2
COLUMN_NAME_LEN: 7
COLUMN_MAX_LEN:  22
====
COLUMN_NAME:     COUNTRY_ID
COLUMN_TYPE:     2
COLUMN_NAME_LEN: 10
COLUMN_MAX_LEN:  22
====
COLUMN_NAME:     CUSTPRODS
COLUMN_TYPE:     100001
COLUMN_NAME_LEN: 9
COLUMN_MAX_LEN:  40
====

Syntax

DBMS_DATA_MINING_TRANSFORM.GET_EXPRESSION (
     expression           IN EXPRESSION_REC,
     chunk_num            IN PLS_INTEGER DEFAULT NULL);
 RETURN VARCHAR2;

Parameters

Usage Notes

1. Chunk numbering starts with one. For chunks outside of the range, the return value is null. When a chunk number is null the whole expression is returned as a string. If the expression is too big, a VALUE_ERROR is raised.

2. See "About Transformation Lists".

3. See "Operational Notes".

Examples

See the example for the SET_EXPRESSION Procedure.

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_AUTOBIN_NUM_EQWIDTH (
     bin_table_name        IN VARCHAR2,
     data_table_name       IN VARCHAR2,
     bin_num               IN PLS_INTEGER DEFAULT 3,
     max_bin_num           IN PLS_INTEGER DEFAULT 100,
     exclude_list          IN COLUMN_LIST DEFAULT NULL,
     round_num             IN PLS_INTEGER DEFAULT 6,
     sample_size           IN PLS_INTEGER DEFAULT 50000,
     bin_schema_name       IN VARCHAR2 DEFAULT NULL,
     data_schema_name      IN VARCHAR2 DEFAULT NULL,
     rem_table_name        IN VARCHAR2 DEFAULT NULL,
     rem_schema_name       IN VARCHAR2 DEFAULT NULL));

Parameters

COL       VARCHAR2(30)
VAL       NUMBER
BIN       VARCHAR2(4000)

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                              ...'coln')

Usage Notes

1. INSERT_AUTOBIN_NUM_EQWIDTH computes the number of bins for a column based on the number of non-null values (COUNT), the maximum (MAX), the minimum (MIN), the standard deviation (STDDEV), and the constant C=3.49/0.9:

   N=floor(power(COUNT,1/3)*(max-min)/(c*dev))
   

   If the sample_size parameter is specified, it is used instead of COUNT.

   See Oracle Database SQL Language Reference for information about the COUNT, MAX, MIN, STDDEV, FLOOR, and POWER functions.

2. INSERT_AUTOBIN_NUM_EQWIDTH uses absolute values to compute the number of bins. The sign of the parameters bin_num, max_bin_num, and sample_size has no effect on the result.

3. In computing the number of bins, INSERT_AUTOBIN_NUM_EQWIDTH evaluates the following criteria in the following order:

   1. The minimum number of bins (bin_num)

   2. The maximum number of bins (max_bin_num)

   3. The maximum number of bins for integer columns, calculated as the number of distinct values in the range max-min+1.

4. The round_num parameter controls the rounding of column values in the transformation definition table, as follows:

   For a value of 308.162:
   when round_num =  1       result is 300
   when round_num =  2       result is 310
   when round_num =  3       result is 308
   when round_num =  0       result is 308.162
   when round_num = -1       result is 308.16
   when round_num = -2       result is 308.2
   

Examples

In this example, INSERT_AUTOBIN_NUM_EQWIDTH computes the bin boundaries for the cust_year_of_birth column in sh.customers and inserts the transformations in a transformation definition table. The STACK_BIN_NUM Procedure creates a transformation list from the contents of the definition table. The CREATE_MODEL Procedure embeds the transformation list in a new model called nb_model.

The transformation and reverse transformation expressions embedded in nb_model are returned by the GET_MODEL_TRANSFORMATIONS Function.

CREATE OR REPLACE VIEW mining_data AS
       SELECT cust_id, cust_year_of_birth, cust_postal_code
       FROM sh.customers;
 
DESCRIBE mining_data
 Name                          Null?    Type
 ----------------------------- -------- ----------------------------
 CUST_ID                       NOT NULL NUMBER
 CUST_YEAR_OF_BIRTH            NOT NULL NUMBER(4)
 CUST_POSTAL_CODE              NOT NULL VARCHAR2(10)
 
BEGIN
  dbms_data_mining_transform.CREATE_BIN_NUM(
     bin_table_name   => 'bin_tbl');
  dbms_data_mining_transform.INSERT_AUTOBIN_NUM_EQWIDTH (
     bin_table_name   => 'bin_tbl',
     data_table_name  => 'mining_data',
     bin_num          => 3,
     max_bin_num      => 5,
     exclude_list     => dbms_data_mining_transform.COLUMN_LIST('cust_id'));
END;
/

set numwidth 4
column val off
SELECT col, val, bin FROM bin_tbl
      ORDER BY val ASC;
 
COL                        VAL BIN
------------------------- ---- -----
CUST_YEAR_OF_BIRTH        1913
CUST_YEAR_OF_BIRTH        1928 1
CUST_YEAR_OF_BIRTH        1944 2
CUST_YEAR_OF_BIRTH        1959 3
CUST_YEAR_OF_BIRTH        1975 4
CUST_YEAR_OF_BIRTH        1990 5

DECLARE
     year_birth_xform   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
     dbms_data_mining_transform.STACK_BIN_NUM (
         bin_table_name           => 'bin_tbl',
         xform_list               =>  year_birth_xform);
     dbms_data_mining.CREATE_MODEL(
         model_name              => 'nb_model',
         mining_function         => dbms_data_mining.classification,
         data_table_name         => 'mining_data',
         case_id_column_name     => 'cust_id',
         target_column_name      => 'cust_postal_code',
         settings_table_name     => null,
         data_schema_name        => null,
         settings_schema_name    => null,
         xform_list              => year_birth_xform);
END;
/
 
SELECT attribute_name 
       FROM TABLE(dbms_data_mining.GET_MODEL_TRANSFORMATIONS('nb_model'));
 
ATTRIBUTE_NAME
------------------------
CUST_YEAR_OF_BIRTH
 
SELECT expression 
       FROM TABLE(dbms_data_mining.GET_MODEL_TRANSFORMATIONS('nb_model'));
 
EXPRESSION
--------------------------------------------------------------------------------
CASE WHEN "CUST_YEAR_OF_BIRTH"<1913 THEN NULL WHEN "CUST_YEAR_OF_BIRTH"<=1928.4
 THEN '1' WHEN "CUST_YEAR_OF_BIRTH"<=1943.8 THEN '2' WHEN "CUST_YEAR_OF_BIRTH"
<=1959.2 THEN '3' WHEN "CUST_YEAR_OF_BIRTH"<=1974.6 THEN '4' WHEN
"CUST_YEAR_OF_BIRTH" <=1990 THEN '5' END
 
SELECT reverse_expression 
       FROM TABLE(dbms_data_mining.GET_MODEL_TRANSFORMATIONS('nb_model'));
 
REVERSE_EXPRESSION
--------------------------------------------------------------------------------
DECODE("CUST_YEAR_OF_BIRTH",'5','(1974.6; 1990]','1','[1913; 1928.4]','2','(1928
.4; 1943.8]','3','(1943.8; 1959.2]','4','(1959.2; 1974.6]',NULL,'( ; 1913), (199
0;  ), NULL')

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_BIN_CAT_FREQ (
     bin_table_name       IN VARCHAR2,
     data_table_name      IN VARCHAR2,
     bin_num              IN PLS_INTEGER DEFAULT 9,
     exclude_list         IN COLUMN_LIST DEFAULT NULL,
     default_num          IN PLS_INTEGER DEFAULT 2,
     bin_support          IN NUMBER DEFAULT NULL,
     bin_schema_name      IN VARCHAR2 DEFAULT NULL,
     data_schema_name     IN VARCHAR2 DEFAULT NULL);

Parameters

COL       VARCHAR2(30)
VAL       VARCHAR2(4000)
BIN       VARCHAR2(4000)

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Usage Notes

If values occur with the same frequency, INSERT_BIN_CAT_FREQ assigns them in descending order when binning is from most to least frequent, or in ascending order when binning is from least to most frequent.

Examples

1. In this example, INSERT_BIN_CAT_FREQ computes the bin boundaries for the cust_postal_code and cust_city columns in sh.customers and inserts the transformations in a transformation definition table. The STACK_BIN_CAT Procedure creates a transformation list from the contents of the definition table, and the CREATE_MODEL Procedure embeds the transformation list in a new model called nb_model.

   The transformation and reverse transformation expressions embedded in nb_model are returned by the GET_MODEL_TRANSFORMATIONS Function.

   CREATE OR REPLACE VIEW mining_data AS
             SELECT cust_id, cust_year_of_birth, cust_postal_code, cust_city
             FROM sh.customers;
    
   DESCRIBE mining_data
    Name                                  Null?    Type
    ------------------------------------- -------- -----------------------------
    CUST_ID                               NOT NULL NUMBER
    CUST_YEAR_OF_BIRTH                    NOT NULL NUMBER(4)
    CUST_POSTAL_CODE                      NOT NULL VARCHAR2(10)
    CUST_CITY                             NOT NULL VARCHAR2(30)
    
   BEGIN
       dbms_data_mining_transform.CREATE_BIN_CAT(
          bin_table_name   => 'bin_tbl_1');
       dbms_data_mining_transform.INSERT_BIN_CAT_FREQ (
          bin_table_name   => 'bin_tbl_1',
          data_table_name  => 'mining_data',
          bin_num          => 4);
   END;
   /
    
   column col format a18
   column val format a15
   column bin format a10
   SELECT col, val, bin 
          FROM bin_tbl_1
          ORDER BY col ASC, bin ASC;
    
   COL                VAL             BIN
   ------------------ --------------- ----------
   CUST_CITY          Los Angeles     1
   CUST_CITY          Greenwich       2
   CUST_CITY          Killarney       3
   CUST_CITY          Montara         4
   CUST_CITY                          5
   CUST_POSTAL_CODE   38082           1
   CUST_POSTAL_CODE   63736           2
   CUST_POSTAL_CODE   55787           3
   CUST_POSTAL_CODE   78558           4
   CUST_POSTAL_CODE                   5
    
   DECLARE
         city_xform   dbms_data_mining_transform.TRANSFORM_LIST;
   BEGIN
         dbms_data_mining_transform.STACK_BIN_CAT (
             bin_table_name           => 'bin_tbl_1',
             xform_list               =>  city_xform);
         dbms_data_mining.CREATE_MODEL(
              model_name              => 'nb_model',
              mining_function         => dbms_data_mining.classification,
              data_table_name         => 'mining_data',
              case_id_column_name     => 'cust_id',
              target_column_name      => 'cust_city',
              settings_table_name     => null,
              data_schema_name        => null,
              settings_schema_name    => null,
              xform_list              => city_xform);
   END;
   /
    
   SELECT attribute_name 
          FROM TABLE(dbms_data_mining.GET_MODEL_TRANSFORMATIONS('nb_model'));
    
   ATTRIBUTE_NAME
   -----------------------------------------------------------------------------
   CUST_CITY
   CUST_POSTAL_CODE
    
   SELECT expression 
          FROM TABLE(dbms_data_mining.GET_MODEL_TRANSFORMATIONS('nb_model'));
    
   EXPRESSION
   -----------------------------------------------------------------------------
   DECODE("CUST_CITY",'Greenwich','2','Killarney','3','Los Angeles','1',
   'Montara','4',NULL,NULL,'5')
   DECODE("CUST_POSTAL_CODE",'38082','1','55787','3','63736','2','78558','4',NULL,NULL,'5')
   
   SELECT reverse_expression 
          FROM TABLE(dbms_data_mining.GET_MODEL_TRANSFORMATIONS('nb_model'));
   
   REVERSE_EXPRESSION
   -----------------------------------------------------------------------------
   DECODE("CUST_CITY",'2','''Greenwich''','3','''Killarney''','1',
   '''Los Angeles''','4','''Montara''',NULL,'NULL','5','DEFAULT')
   DECODE("CUST_POSTAL_CODE",'1','''38082''','3','''55787''','2','''63736''',
   '4','''78558''',NULL,'NULL','5','DEFAULT')
   

2. The binning order in example 1 is from most frequent to least frequent. The following example shows reverse order binning (least frequent to most frequent). The binning order is reversed by setting bin_num to -4 instead of 4.

   BEGIN
       dbms_data_mining_transform.CREATE_BIN_CAT(
           bin_table_name   => 'bin_tbl_reverse');
       dbms_data_mining_transform.INSERT_BIN_CAT_FREQ (
           bin_table_name   => 'bin_tbl_reverse',
           data_table_name  => 'mining_data',
           bin_num          => -4);
    END;
    /
    
   column col format a20
   SELECT col, val, bin 
          FROM bin_tbl_reverse
          ORDER BY col ASC, bin ASC;
    
   COL                  VAL             BIN
   -------------------- --------------- ----------
   CUST_CITY            Tokyo           1
   CUST_CITY            Sliedrecht      2
   CUST_CITY            Haarlem         3
   CUST_CITY            Diemen          4
   CUST_CITY                            5
   CUST_POSTAL_CODE     49358           1
   CUST_POSTAL_CODE     80563           2
   CUST_POSTAL_CODE     74903           3
   CUST_POSTAL_CODE     71349           4
   CUST_POSTAL_CODE                     5
   

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_BIN_NUM_EQWIDTH (
     bin_table_name        IN VARCHAR2,
     data_table_name       IN VARCHAR2,
     bin_num               IN PLS_INTEGER DEFAULT 10,
     exclude_list          IN COLUMN_LIST DEFAULT NULL,
     round_num             IN PLS_INTEGER DEFAULT 6,
     bin_schema_name       IN VARCHAR2 DEFAULT NULL,
     data_schema_name      IN VARCHAR2 DEFAULT NULL);

Parameters

COL       VARCHAR2(30)
VAL       NUMBER
BIN       VARCHAR2(4000)

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Usage Notes

1. The round_num parameter controls the rounding of column values in the transformation definition table, as follows:

   For a value of 308.162:
   when round_num =  1       result is 300
   when round_num =  2       result is 310
   when round_num =  3       result is 308
   when round_num =  0       result is 308.162
   when round_num = -1       result is 308.16
   when round_num = -2       result is 308.2
   

2. INSERT_BIN_NUM_EQWIDTH ignores columns with all NULL values or only one unique value.

Examples

In this example, INSERT_BIN_NUM_EQWIDTH computes the bin boundaries for the affinity_card column in mining_data_build and inserts the transformations in a transformation definition table. The STACK_BIN_NUM Procedure creates a transformation list from the contents of the definition table. The CREATE_MODEL Procedure embeds the transformation list in a new model called glm_model.

The transformation and reverse transformation expressions embedded in glm_model are returned by the GET_MODEL_TRANSFORMATIONS Function.

CREATE OR REPLACE VIEW mining_data AS
       SELECT cust_id, cust_income_level, cust_gender, affinity_card
       FROM mining_data_build;
 
DESCRIBE mining_data
 Name                      Null?    Type
 ------------------------- -------- -----------------
 CUST_ID                   NOT NULL NUMBER
 CUST_INCOME_LEVEL                  VARCHAR2(30)
 CUST_GENDER                        VARCHAR2(1)
 AFFINITY_CARD                      NUMBER(10)
 
BEGIN
    dbms_data_mining_transform.CREATE_BIN_NUM(
        bin_table_name   => 'bin_tbl');
    dbms_data_mining_transform.INSERT_BIN_NUM_EQWIDTH (
        bin_table_name   => 'bin_tbl',
        data_table_name  => 'mining_data',
        bin_num          => 4,
        exclude_list     => dbms_data_mining_transform.COLUMN_LIST('cust_id'));
END;
/
 
set numwidth 10
column val off
column col format a20
column bin format a10
SELECT col, val, bin FROM bin_tbl
    ORDER BY val ASC;
 
COL                         VAL  BIN
-------------------- ----------  ----------
AFFINITY_CARD                 0
AFFINITY_CARD               .25  1
AFFINITY_CARD                .5  2
AFFINITY_CARD               .75  3
AFFINITY_CARD                 1  4
 
CREATE TABLE glmsettings(
        setting_name  VARCHAR2(30),
        setting_value VARCHAR2(30));
 
BEGIN
   INSERT INTO glmsettings (setting_name, setting_value) VALUES
         (dbms_data_mining.algo_name, dbms_data_mining.algo_generalized_linear_model);
   COMMIT;
END;
/
 
DECLARE
     xforms   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
     dbms_data_mining_transform.STACK_BIN_NUM (
         bin_table_name           => 'bin_tbl',
         xform_list               =>  xforms,
         literal_flag             =>  TRUE);
     dbms_data_mining.CREATE_MODEL(
         model_name              => 'glm_model',
         mining_function         => dbms_data_mining.regression,
         data_table_name         => 'mining_data',
         case_id_column_name     => 'cust_id',
         target_column_name      => 'affinity_card',
         settings_table_name     => 'glmsettings',
         data_schema_name        => null,
         settings_schema_name    => null,
         xform_list              => xforms);
END;
/
 
SELECT attribute_name 
      FROM TABLE(dbms_data_mining.GET_MODEL_TRANSFORMATIONS('glm_model'));
 
ATTRIBUTE_NAME
------------------------
AFFINITY_CARD
 
SELECT expression 
       FROM TABLE(dbms_data_mining.GET_MODEL_TRANSFORMATIONS('glm_model'));
 
EXPRESSION
--------------------------------------------------------------------------------
CASE WHEN "AFFINITY_CARD"<0 THEN NULL WHEN "AFFINITY_CARD"<=.25 THEN 1 WHEN
"AFFINITY_CARD"<=.5 THEN 2 WHEN "AFFINITY_CARD"<=.75 THEN 3 WHEN
"AFFINITY_CARD"<=1 THEN 4 END
 
SELECT reverse_expression 
       FROM TABLE(dbms_data_mining.GET_MODEL_TRANSFORMATIONS('glm_model'));
 
REVERSE_EXPRESSION
--------------------------------------------------------------------------------
DECODE("AFFINITY_CARD",4,'(.75; 1]',1,'[0; .25]',2,'(.25; .5]',3,'(.5; .75]',
NULL,'( ; 0), (1;  ), NULL')

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_BIN_NUM_QTILE (
    bin_table_name       IN VARCHAR2,
    data_table_name      IN VARCHAR2,
    bin_num              IN PLS_INTEGER DEFAULT 10,
    exclude_list         IN COLUMN_LIST DEFAULT NULL,
    bin_schema_name      IN VARCHAR2 DEFAULT NULL,
    data_schema_name     IN VARCHAR2 DEFAULT NULL);

Parameters

COL       VARCHAR2(30)
VAL       NUMBER
BIN       VARCHAR2(4000)

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Usage Notes

1. After dividing the data into quantiles, the NTILE function distributes any remainder values one for each quantile, starting with the first. See Oracle Database SQL Language Reference for details.

2. Columns with all NULL values are ignored by INSERT_BIN_NUM_QTILE.

Examples

In this example, INSERT_BIN_NUM_QTILE computes the bin boundaries for the cust_year_of_birth and cust_credit_limit columns in sh.customers and inserts the transformations in a transformation definition table. The STACK_BIN_NUM Procedure creates a transformation list from the contents of the definition table.

The SQL expression that computes the transformation is shown in STACK_VIEW. The view is for display purposes only; it cannot be used to embed the transformations in a model.

CREATE OR REPLACE VIEW mining_data AS
        SELECT cust_id, cust_year_of_birth, cust_credit_limit, cust_city
        FROM sh.customers;
 
DESCRIBE mining_data
 Name                                    Null?    Type
 --------------------------------------- -------- -----------------------------
 CUST_ID                                 NOT NULL NUMBER
 CUST_YEAR_OF_BIRTH                      NOT NULL NUMBER(4)
 CUST_CREDIT_LIMIT                       NUMBER
 CUST_CITY                               NOT NULL VARCHAR2(30)
 
BEGIN
   dbms_data_mining_transform.CREATE_BIN_NUM(
        bin_table_name   => 'bin_tbl');
   dbms_data_mining_transform.INSERT_BIN_NUM_QTILE (
        bin_table_name   => 'bin_tbl',
        data_table_name  => 'mining_data',
        bin_num          => 3,
        exclude_list     => dbms_data_mining_transform.COLUMN_LIST('cust_id'));
END;
/
 
set numwidth 8
column val off
column col format a20
column bin format a10
SELECT col, val, bin
      FROM bin_tbl
      ORDER BY col ASC, val ASC;
 
COL                       VAL BIN
-------------------- -------- ----------
CUST_CREDIT_LIMIT        1500
CUST_CREDIT_LIMIT        3000 1
CUST_CREDIT_LIMIT        9000 2
CUST_CREDIT_LIMIT       15000 3
CUST_YEAR_OF_BIRTH       1913
CUST_YEAR_OF_BIRTH       1949 1
CUST_YEAR_OF_BIRTH       1965 2
CUST_YEAR_OF_BIRTH       1990 3
 
DECLARE
   xforms   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
   dbms_data_mining_transform.STACK_BIN_NUM (
        bin_table_name        => 'bin_tbl',
        xform_list            =>  xforms);
   dbms_data_mining_transform.XFORM_STACK (
        xform_list            =>  xforms,
        data_table_name       => 'mining_data',
        xform_view_name       => 'stack_view');
END;
/
 
set long 3000
SELECT text FROM user_views WHERE view_name in 'STACK_VIEW';
 
TEXT
--------------------------------------------------------------------------------
SELECT "CUST_ID",CASE WHEN "CUST_YEAR_OF_BIRTH"<1913 THEN NULL WHEN "CUST_YEAR_O
F_BIRTH"<=1949 THEN '1' WHEN "CUST_YEAR_OF_BIRTH"<=1965 THEN '2' WHEN "CUST_YEAR
_OF_BIRTH"<=1990 THEN '3' END "CUST_YEAR_OF_BIRTH",CASE WHEN "CUST_CREDIT_LIMIT"
<1500 THEN NULL WHEN "CUST_CREDIT_LIMIT"<=3000 THEN '1' WHEN "CUST_CREDIT_LIMIT"
<=9000 THEN '2' WHEN "CUST_CREDIT_LIMIT"<=15000 THEN '3' END "CUST_CREDIT_LIMIT"
,"CUST_CITY" FROM mining_data

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_BIN_SUPER (
    num_table_name        IN VARCHAR2,
    cat_table_name        IN VARCHAR2,
    data_table_name       IN VARCHAR2,
    target_column_name    IN VARCHAR2,
    max_bin_num           IN PLS_INTEGER  DEFAULT 1000,
    exclude_list          IN COLUMN_LIST  DEFAULT NULL,
    num_schema_name       IN VARCHAR2     DEFAULT NULL,
    cat_schema_name       IN VARCHAR2     DEFAULT NULL,
    data_schema_name      IN VARCHAR2     DEFAULT NULL,
    rem_table_name        IN VARCHAR2     DEFAULT NULL,
    rem_schema_name       IN VARCHAR2     DEFAULT NULL);

Parameters

COL       VARCHAR2(30)
VAL       VNUMBER
BIN       VARCHAR2(4000)

COL       VARCHAR2(30)
VAL       VARCHAR2(4000)
BIN       VARCHAR2(4000)

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Usage Notes

1. Columns that have no significant splits are not binned. You can remove the unbinned columns from the mining data by specifying a column removal definition table. If you do not specify a column removal definition table, the unbinned columns remain in the mining data.

2. See Oracle Data Mining Concepts to learn more about decision trees in Oracle Data Mining

Examples

In this example, INSERT_BIN_SUPER computes the bin boundaries for predictors of cust_credit_limit and inserts the transformations in transformation definition tables. One predictor is numerical, the other is categorical. (INSERT_BIN_SUPER determines that the cust_postal_code column is not a significant predictor.) STACK procedures create transformation lists from the contents of the definition tables.

The SQL expressions that compute the transformations are shown in the views MINING_DATA_STACK_NUM and MINING_DATA_STACK_CAT. The views are for display purposes only; they cannot be used to embed the transformations in a model.

CREATE OR REPLACE VIEW mining_data AS
     SELECT cust_id, cust_year_of_birth, cust_marital_status,
            cust_postal_code, cust_credit_limit
     FROM sh.customers;
 
DESCRIBE mining_data
 Name                             Null?    Type
 -------------------------------- -------- ------------------------------------
 CUST_ID                          NOT NULL NUMBER
 CUST_YEAR_OF_BIRTH               NOT NULL NUMBER(4)
 CUST_MARITAL_STATUS                       VARCHAR2(20)
 CUST_POSTAL_CODE                 NOT NULL VARCHAR2(10)
 CUST_CREDIT_LIMIT                         NUMBER
 
BEGIN
    dbms_data_mining_transform.CREATE_BIN_NUM(
         bin_table_name      => 'bin_num_tbl');
    dbms_data_mining_transform.CREATE_BIN_CAT(
         bin_table_name      => 'bin_cat_tbl');
    dbms_data_mining_transform.CREATE_COL_REM(
         rem_table_name      => 'rem_tbl');
END;
/
 
BEGIN
   COMMIT;
   dbms_data_mining_transform.INSERT_BIN_SUPER (
      num_table_name      => 'bin_num_tbl',
      cat_table_name      => 'bin_cat_tbl',
      data_table_name     => 'mining_data',
      target_column_name  => 'cust_credit_limit',
      max_bin_num         =>  4,
      exclude_list        =>  dbms_data_mining_transform.COLUMN_LIST('cust_id'),
      num_schema_name     => 'dmuser',
      cat_schema_name     => 'dmuser',
      data_schema_name    => 'dmuser',
      rem_table_name      => 'rem_tbl',
      rem_schema_name     => 'dmuser');
   COMMIT;
END;
/
 
set numwidth 8
column val off
SELECT col, val, bin FROM bin_num_tbl
      ORDER BY bin ASC;
 
COL                       VAL BIN
-------------------- -------- ----------
CUST_YEAR_OF_BIRTH     1923.5 1
CUST_YEAR_OF_BIRTH     1923.5 1
CUST_YEAR_OF_BIRTH     1945.5 2
CUST_YEAR_OF_BIRTH     1980.5 3
CUST_YEAR_OF_BIRTH            4
 
column val on
column val format a20
SELECT col, val, bin FROM bin_cat_tbl
      ORDER BY bin ASC;
 
COL                  VAL                  BIN
-------------------- -------------------- ----------
CUST_MARITAL_STATUS  married              1
CUST_MARITAL_STATUS  single               2
CUST_MARITAL_STATUS  Mar-AF               3
CUST_MARITAL_STATUS  Mabsent              3
CUST_MARITAL_STATUS  Divorc.              3
CUST_MARITAL_STATUS  Married              3
CUST_MARITAL_STATUS  Widowed              3
CUST_MARITAL_STATUS  NeverM               3
CUST_MARITAL_STATUS  Separ.               3
CUST_MARITAL_STATUS  divorced             4
CUST_MARITAL_STATUS  widow                4
 
SELECT col from rem_tbl;
 
COL
--------------------
CUST_POSTAL_CODE
 
DECLARE
    xforms_num      dbms_data_mining_transform.TRANSFORM_LIST;
    xforms_cat      dbms_data_mining_transform.TRANSFORM_LIST;
    BEGIN
       dbms_data_mining_transform.STACK_BIN_NUM (
            bin_table_name    => 'bin_num_tbl',
            xform_list        => xforms_num);
       dbms_data_mining_transform.XFORM_STACK (
            xform_list         => xforms_num,
            data_table_name    => 'mining_data',
            xform_view_name    => 'mining_data_stack_num');
       dbms_data_mining_transform.STACK_BIN_CAT (
             bin_table_name    => 'bin_cat_tbl',
             xform_list        => xforms_cat);
       dbms_data_mining_transform.XFORM_STACK (
             xform_list         => xforms_cat,
             data_table_name    => 'mining_data',
             xform_view_name    => 'mining_data_stack_cat');
   END;
 /
 
set long 3000
SELECT text FROM user_views WHERE view_name IN 'MINING_DATA_STACK_NUM';
 
TEXT
--------------------------------------------------------------------------------
SELECT "CUST_ID",CASE WHEN "CUST_YEAR_OF_BIRTH"<1923.5 THEN '1' WHEN "CUST_YEAR_
OF_BIRTH"<=1923.5 THEN '1' WHEN "CUST_YEAR_OF_BIRTH"<=1945.5 THEN '2' WHEN "CUST
_YEAR_OF_BIRTH"<=1980.5 THEN '3' WHEN "CUST_YEAR_OF_BIRTH" IS NOT NULL THEN '4'
END "CUST_YEAR_OF_BIRTH","CUST_MARITAL_STATUS","CUST_POSTAL_CODE","CUST_CREDIT_L
IMIT" FROM mining_data
 
 
SELECT text FROM user_views WHERE view_name IN 'MINING_DATA_STACK_CAT';
 
TEXT
--------------------------------------------------------------------------------
SELECT "CUST_ID","CUST_YEAR_OF_BIRTH",DECODE("CUST_MARITAL_STATUS",'Divorc.','3'
,'Mabsent','3','Mar-AF','3','Married','3','NeverM','3','Separ.','3','Widowed','3
','divorced','4','married','1','single','2','widow','4') "CUST_MARITAL_STATUS","
CUST_POSTAL_CODE","CUST_CREDIT_LIMIT" FROM mining_data

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_CLIP_TRIM_TAIL (
    clip_table_name     IN VARCHAR2,
    data_table_name     IN VARCHAR2,
    tail_frac           IN NUMBER DEFAULT 0.025,
    exclude_list        IN COLUMN_LIST DEFAULT NULL,
    clip_schema_name    IN VARCHAR2 DEFAULT NULL,
    data_schema_name    IN VARCHAR2 DEFAULT NULL);

Parameters

 COL         VARCHAR2(30)
 LCUT        NUMBER
 LVAL        NUMBER
 RCUT        NUMBER
 RVAL        NUMBER

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Usage Notes

The DBMS_DATA_MINING_TRANSFORM package provides two clipping procedures: INSERT_CLIP_TRIM_TAIL and INSERT_CLIP_WINSOR_TAIL. Both procedures compute the boundaries as follows:

• Count the number of non-null values, n, and sort them in ascending order

• Calculate the number of outliers, t, as n*tail_frac

• Define the lower boundary lcut as the value at position 1+floor(t)

• Define the upper boundary rcut as the value at position n-floor(t)

  (The SQL FLOOR function returns the largest integer less than or equal to t.)

• All values that are <= lcut or => rcut are designated as outliers.

INSERT_CLIP_TRIM_TAIL replaces the outliers with nulls, effectively removing them from the data.

INSERT_CLIP_WINSOR_TAIL assigns lcut to the low outliers and rcut to the high outliers.

Examples

In this example, INSERT_CLIP_TRIM_TAIL trims 10% of the data in two columns (5% from the high end and 5% from the low end) and inserts the transformations in a transformation definition table. The STACK_CLIP Procedure creates a transformation list from the contents of the definition table.

The SQL expression that computes the trimming is shown in the view MINING_DATA_STACK. The view is for display purposes only; it cannot be used to embed the transformations in a model.

CREATE OR REPLACE VIEW mining_data AS
       SELECT cust_id, cust_year_of_birth, cust_credit_limit, cust_city
       FROM sh.customers;
 
DESCRIBE mining_data
 Name                            Null?    Type
 ------------------------------- -------- -------------------
 CUST_ID                         NOT NULL NUMBER
 CUST_YEAR_OF_BIRTH              NOT NULL NUMBER(4)
 CUST_CREDIT_LIMIT                        NUMBER
 CUST_CITY                       NOT NULL VARCHAR2(30)

BEGIN
   dbms_data_mining_transform.CREATE_CLIP(
      clip_table_name    => 'clip_tbl');
   dbms_data_mining_transform.INSERT_CLIP_TRIM_TAIL(
      clip_table_name    => 'clip_tbl',
      data_table_name    => 'mining_data',
      tail_frac          => 0.05,
      exclude_list       => DBMS_DATA_MINING_TRANSFORM.COLUMN_LIST('cust_id'));
END;
/
 
SELECT col, lcut, lval, rcut, rval
      FROM clip_tbl
      ORDER BY col ASC;
 
COL                      LCUT     LVAL     RCUT     RVAL
-------------------- -------- -------- -------- --------
CUST_CREDIT_LIMIT        1500             11000
CUST_YEAR_OF_BIRTH       1934              1982
 
DECLARE
     xforms      dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
     dbms_data_mining_transform.STACK_CLIP (
          clip_table_name    => 'clip_tbl',
          xform_list         => xforms);
     dbms_data_mining_transform.XFORM_STACK (
          xform_list         => xforms,
          data_table_name    => 'mining_data',
          xform_view_name    => 'mining_data_stack');
 END;
 /
 
set long 3000
SELECT text FROM user_views WHERE view_name IN 'MINING_DATA_STACK';
 
TEXT
--------------------------------------------------------------------------------
SELECT "CUST_ID",CASE WHEN "CUST_YEAR_OF_BIRTH" < 1934 THEN NULL WHEN "CUST_YEAR
_OF_BIRTH" > 1982 THEN NULL ELSE "CUST_YEAR_OF_BIRTH" END "CUST_YEAR_OF_BIRTH",C
ASE WHEN "CUST_CREDIT_LIMIT" < 1500 THEN NULL WHEN "CUST_CREDIT_LIMIT" > 11000 T
HEN NULL ELSE "CUST_CREDIT_LIMIT" END "CUST_CREDIT_LIMIT","CUST_CITY" FROM minin
g_data

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_CLIP_WINSOR_TAIL (
    clip_table_name    IN VARCHAR2,
    data_table_name    IN VARCHAR2,
    tail_frac          IN NUMBER DEFAULT 0.025,
    exclude_list       IN COLUMN_LIST DEFAULT NULL,
    clip_schema_name   IN VARCHAR2 DEFAULT NULL,
    data_schema_name   IN VARCHAR2 DEFAULT NULL);

Parameters

 COL         VARCHAR2(30)
 LCUT        NUMBER
 LVAL        NUMBER
 RCUT        NUMBER
 RVAL        NUMBER

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Usage Notes

The DBMS_DATA_MINING_TRANSFORM package provides two clipping procedures: INSERT_CLIP_WINSOR_TAIL and INSERT_CLIP_TRIM_TAIL. Both procedures compute the boundaries as follows:

• Count the number of non-null values, n, and sort them in ascending order

• Calculate the number of outliers, t, as n*tail_frac

• Define the lower boundary lcut as the value at position 1+floor(t)

• Define the upper boundary rcut as the value at position n-floor(t)

  (The SQL FLOOR function returns the largest integer less than or equal to t.)

• All values that are <= lcut or => rcut are designated as outliers.

INSERT_CLIP_WINSOR_TAIL assigns lcut to the low outliers and rcut to the high outliers.

INSERT_CLIP_TRIM_TAIL replaces the outliers with nulls, effectively removing them from the data.

Examples

In this example, INSERT_CLIP_WINSOR_TAIL winsorizes 10% of the data in two columns (5% from the high end, and 5% from the low end) and inserts the transformations in a transformation definition table. The STACK_CLIP Procedure creates a transformation list from the contents of the definition table.

The SQL expression that computes the transformation is shown in the view MINING_DATA_STACK. The view is for display purposes only; it cannot be used to embed the transformations in a model.

CREATE OR REPLACE VIEW mining_data AS
        SELECT cust_id, cust_year_of_birth, cust_credit_limit, cust_city
        FROM sh.customers;

describe mining_data
 Name                                     Null?    Type
 ---------------------------------------- -------- -------------
 CUST_ID                                  NOT NULL NUMBER
 CUST_YEAR_OF_BIRTH                       NOT NULL NUMBER(4)
 CUST_CREDIT_LIMIT                                 NUMBER
 CUST_CITY                                NOT NULL VARCHAR2(30)
 
BEGIN
  dbms_data_mining_transform.CREATE_CLIP(
      clip_table_name   => 'clip_tbl');
  dbms_data_mining_transform.INSERT_CLIP_WINSOR_TAIL(
      clip_table_name   => 'clip_tbl',
      data_table_name   => 'mining_data',
      tail_frac         => 0.05,
      exclude_list      => DBMS_DATA_MINING_TRANSFORM.COLUMN_LIST('cust_id'));
END;
/

SELECT col, lcut, lval, rcut, rval FROM clip_tbl
   ORDER BY col ASC;
COL                                LCUT     LVAL     RCUT     RVAL
------------------------------ -------- -------- -------- --------
CUST_CREDIT_LIMIT                  1500     1500    11000    11000
CUST_YEAR_OF_BIRTH                 1934     1934     1982     1982

DECLARE
   xforms      dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
   dbms_data_mining_transform.STACK_CLIP (
   clip_table_name    => 'clip_tbl',
   xform_list        => xforms);
dbms_data_mining_transform.XFORM_STACK (
   xform_list         => xforms,
   data_table_name    => 'mining_data',
   xform_view_name    => 'mining_data_stack');
END;
/
 
set long 3000
SQL> SELECT text FROM user_views WHERE view_name IN 'MINING_DATA_STACK';
 
TEXT
--------------------------------------------------------------------------------
SELECT "CUST_ID",CASE WHEN "CUST_YEAR_OF_BIRTH" < 1934 THEN 1934 WHEN "CUST_YEAR
_OF_BIRTH" > 1982 THEN 1982 ELSE "CUST_YEAR_OF_BIRTH" END "CUST_YEAR_OF_BIRTH",C
ASE WHEN "CUST_CREDIT_LIMIT" < 1500 THEN 1500 WHEN "CUST_CREDIT_LIMIT" > 11000 T
HEN 11000 ELSE "CUST_CREDIT_LIMIT" END "CUST_CREDIT_LIMIT","CUST_CITY" FROM mini
ng_data

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_MISS_CAT_MODE (
    miss_table_name    IN VARCHAR2,
    data_table_name    IN VARCHAR2,
    exclude_list       IN COLUMN_LIST DEFAULT NULL,
    miss_schema_name   IN VARCHAR2 DEFAULT NULL,
    data_schema_name   IN VARCHAR2 DEFAULT NULL);

Parameters

 COL         VARCHAR2(30)
 VAL         VARCHAR2(4000)

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Usage Notes

If you wish to replace categorical missing values with a value other than the mode, you can edit the transformation definition table.

Example

In this example, INSERT_MISS_CAT_MODE computes missing value treatment for cust_city and inserts the transformation in a transformation definition table. The STACK_MISS_CAT Procedure creates a transformation list from the contents of the definition table.

The SQL expression that computes the transformation is shown in the view MINING_DATA_STACK. The view is for display purposes only; it cannot be used to embed the transformations in a model.

CREATE OR REPLACE VIEW mining_data AS
         SELECT cust_id, cust_year_of_birth, cust_city
         FROM sh.customers;
 
describe mining_data
 Name                             Null?    Type
 -------------------------------- -------- ----------------
 CUST_ID                          NOT NULL NUMBER
 CUST_YEAR_OF_BIRTH               NOT NULL NUMBER(4)
 CUST_CITY                        NOT NULL VARCHAR2(30)
 
BEGIN
  dbms_data_mining_transform.create_miss_cat(
      miss_table_name   => 'missc_tbl');
  dbms_data_mining_transform.insert_miss_cat_mode(
      miss_table_name   => 'missc_tbl',
      data_table_name   => 'mining_data');
END;
/

SELECT stats_mode(cust_city) FROM mining_data;
 
STATS_MODE(CUST_CITY)
------------------------------
Los Angeles

SELECT col, val
    from missc_tbl;

COL                            VAL
------------------------------ ------------------------------
CUST_CITY                      Los Angeles

DECLARE
    xforms      dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
    dbms_data_mining_transform.STACK_MISS_CAT (
        miss_table_name    => 'missc_tbl',
        xform_list        => xforms);
    dbms_data_mining_transform.XFORM_STACK (
         xform_list         => xforms,
         data_table_name    => 'mining_data',
         xform_view_name    => 'mining_data_stack');
END;
/
 
set long 3000
SELECT text FROM user_views WHERE view_name IN 'MINING_DATA_STACK';
 
TEXT
--------------------------------------------------------------------------------
SELECT "CUST_ID","CUST_YEAR_OF_BIRTH",NVL("CUST_CITY",'Los Angeles') "CUST_CITY"
 FROM mining_data

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_MISS_NUM_MEAN (
    miss_table_name    IN VARCHAR2,
    data_table_name    IN VARCHAR2,
    exclude_list       IN COLUMN_LIST DEFAULT NULL,
    round_num          IN PLS_INTEGER DEFAULT 6,
    miss_schema_name   IN VARCHAR2 DEFAULT NULL,
    data_schema_name   IN VARCHAR2 DEFAULT NULL);

Parameters

 COL          VARCHAR2(30)
 VAL          NUMBER

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Usage Notes

If you wish to replace numerical missing values with a value other than the mean, you can edit the transformation definition table.

Example

In this example, INSERT_MISS_NUM_MEAN computes missing value treatment for cust_year_of_birth and inserts the transformation in a transformation definition table. The STACK_MISS_NUM Procedure creates a transformation list from the contents of the definition table.

The SQL expression that computes the transformation is shown in the view MINING_DATA_STACK. The view is for display purposes only; it cannot be used to embed the transformations in a model.

CREATE OR REPLACE VIEW mining_data AS
    SELECT cust_id, cust_year_of_birth, cust_city
    FROM sh.customers;

DESCRIBE mining_data
 Name                                       Null?    Type
 ------------------------------------------ -------- -------------------
 CUST_ID                                    NOT NULL NUMBER
 CUST_YEAR_OF_BIRTH                         NOT NULL NUMBER(4)
 CUST_CITY                                  NOT NULL VARCHAR2(30)
 
BEGIN
   dbms_data_mining_transform.create_miss_num(
       miss_table_name   => 'missn_tbl');
   dbms_data_mining_transform.insert_miss_num_mean(
       miss_table_name   => 'missn_tbl',
       data_table_name   => 'mining_data',
       exclude_list      => DBMS_DATA_MINING_TRANSFORM.COLUMN_LIST('cust_id'));
END;
/
 
set numwidth 4
column val off
SELECT col, val
  FROM missn_tbl;
 
COL                   VAL
-------------------- ----
CUST_YEAR_OF_BIRTH   1957
 
SELECT avg(cust_year_of_birth) FROM mining_data;
 
AVG(CUST_YEAR_OF_BIRTH)
-----------------------
                   1957
 
DECLARE
    xforms      dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
    dbms_data_mining_transform.STACK_MISS_NUM (
         miss_table_name    => 'missn_tbl',
         xform_list        => xforms);
    dbms_data_mining_transform.XFORM_STACK (
         xform_list         => xforms,
         data_table_name    => 'mining_data',
         xform_view_name    => 'mining_data_stack');
END;
/
 
set long 3000
SELECT text FROM user_views WHERE view_name IN 'MINING_DATA_STACK';
 
TEXT
--------------------------------------------------------------------------------
SELECT "CUST_ID",NVL("CUST_YEAR_OF_BIRTH",1957.4) "CUST_YEAR_OF_BIRTH","CUST_CIT
Y" FROM mining_data

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_NORM_LIN_MINMAX (
     norm_table_name     IN VARCHAR2,
     data_table_name     IN VARCHAR2,
     exclude_list        IN COLUMN_LIST DEFAULT NULL,
     round_num           IN PLS_INTEGER DEFAULT 6,
     norm_schema_name    IN VARCHAR2 DEFAULT NULL,
     data_schema_name    IN VARCHAR2 DEFAULT NULL);

Parameters

 COL          VARCHAR2(30)
 SHIFT        NUMBER
 SCALE        NUMBER

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Examples

In this example, INSERT_NORM_LIN_MINMAX normalizes the cust_year_of_birth column and inserts the transformation in a transformation definition table. The STACK_NORM_LIN Procedure creates a transformation list from the contents of the definition table.

The SQL expression that computes the transformation is shown in the view MINING_DATA_STACK. The view is for display purposes only; it cannot be used to embed the transformations in a model.

CREATE OR REPLACE VIEW mining_data AS
         SELECT cust_id, cust_gender, cust_year_of_birth
         FROM sh.customers;

describe mining_data
 Name                                 Null?    Type
 ------------------------------------ -------- ----------------
 CUST_ID                              NOT NULL NUMBER
 CUST_GENDER                          NOT NULL CHAR(1)
 CUST_YEAR_OF_BIRTH                   NOT NULL NUMBER(4)
 
BEGIN
       dbms_data_mining_transform.CREATE_NORM_LIN(
         norm_table_name  => 'norm_tbl');
       dbms_data_mining_transform.INSERT_NORM_LIN_MINMAX(
         norm_table_name  => 'norm_tbl',
         data_table_name  => 'mining_data',
         exclude_list     => dbms_data_mining_transform.COLUMN_LIST( 'cust_id'),
         round_num        => 3);
END;
/
 
SELECT col, shift, scale FROM norm_tbl;
 
COL                                 SHIFT      SCALE
------------------------------ ---------- ----------
CUST_YEAR_OF_BIRTH                   1910         77

DECLARE
     xforms      dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
     dbms_data_mining_transform.STACK_NORM_LIN (
          norm_table_name    => 'norm_tbl',
          xform_list        => xforms);
     dbms_data_mining_transform.XFORM_STACK (
          xform_list         => xforms,
          data_table_name    => 'mining_data',
          xform_view_name    => 'mining_data_stack');
END;
/
 
set long 3000
SELECT text FROM user_views WHERE view_name IN 'MINING_DATA_STACK';
 
TEXT
--------------------------------------------------------------------------------
SELECT "CUST_ID","CUST_GENDER",("CUST_YEAR_OF_BIRTH"-1910)/77 "CUST_YEAR_OF_BIRT
H" FROM mining_data

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_NORM_LIN_SCALE (
     norm_table_name     IN VARCHAR2,
     data_table_name     IN VARCHAR2,
     exclude_list        IN COLUMN_LIST DEFAULT NULL,
     round_num           IN PLS_INTEGER DEFAULT 6,
     norm_schema_name    IN VARCHAR2 DEFAULT NULL,
     data_schema_name    IN VARCHAR2 DEFAULT NULL);

Parameters

 COL       VARCHAR2(30)
 SHIFT     NUMBER
 SCALE     NUMBER

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Examples

In this example, INSERT_NORM_LIN_SCALE normalizes the cust_year_of_birth column and inserts the transformation in a transformation definition table. The STACK_NORM_LIN Procedure creates a transformation list from the contents of the definition table.

The SQL expression that computes the transformation is shown in the view MINING_DATA_STACK. The view is for display purposes only; it cannot be used to embed the transformations in a model.

CREATE OR REPLACE VIEW mining_data AS
      SELECT cust_id, cust_gender, cust_year_of_birth
      FROM sh.customers;

DESCRIBE mining_data
 Name                               Null?    Type
 ---------------------------------- -------- ------------------
 CUST_ID                            NOT NULL NUMBER
 CUST_GENDER                        NOT NULL CHAR(1)
 CUST_YEAR_OF_BIRTH                 NOT NULL NUMBER(4)
 
BEGIN
   dbms_data_mining_transform.CREATE_NORM_LIN(
       norm_table_name  => 'norm_tbl');
       dbms_data_mining_transform.INSERT_NORM_LIN_SCALE(
       norm_table_name  => 'norm_tbl',
       data_table_name  => 'mining_data',
       exclude_list     => dbms_data_mining_transform.COLUMN_LIST( 'cust_id'),
       round_num        => 3);
 END;
 /
 
SELECT col, shift, scale FROM norm_tbl;
 
COL                  SHIFT SCALE
-------------------- ----- -----
CUST_YEAR_OF_BIRTH       0  1990
 
DECLARE
    xforms      dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
    dbms_data_mining_transform.STACK_NORM_LIN (
        norm_table_name    => 'norm_tbl',
        xform_list        => xforms);
    dbms_data_mining_transform.XFORM_STACK (
        xform_list         => xforms,
        data_table_name    => 'mining_data',
        xform_view_name    => 'mining_data_stack');
END;
/
 
set long 3000
SELECT text FROM user_views WHERE view_name IN 'MINING_DATA_STACK';
 
TEXT
--------------------------------------------------------------------------------
SELECT "CUST_ID","CUST_GENDER",("CUST_YEAR_OF_BIRTH"-0)/1990 "CUST_YEAR_OF_BIRTH
" FROM mining_data

Syntax

DBMS_DATA_MINING_TRANSFORM.INSERT_NORM_LIN_ZSCORE (
     norm_table_name     IN VARCHAR2,
     data_table_name     IN VARCHAR2,
     exclude_list        IN COLUMN_LIST DEFAULT NULL,
     round_num           IN PLS_INTEGER DEFAULT 6,
     norm_schema_name    IN VARCHAR2 DEFAULT NULL,
     data_schema_name    IN VARCHAR2 DEFAULT NULL);

Parameters

 COL       VARCHAR2(30)
 SHIFT     NUMBER
 SCALE     NUMBER

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Examples

In this example, INSERT_NORM_LIN_ZSCORE normalizes the cust_year_of_birth column and inserts the transformation in a transformation definition table. The STACK_NORM_LIN Procedure creates a transformation list from the contents of the definition table.

The SQL expression that computes the transformation is shown in the view MINING_DATA_STACK. The view is for display purposes only; it cannot be used to embed the transformations in a model.

CREATE OR REPLACE VIEW mining_data AS
       SELECT cust_id, cust_gender, cust_year_of_birth
       FROM sh.customers;
 
DESCRIBE mining_data
 Name                                Null?    Type
 ----------------------------------- -------- --------------------
 CUST_ID                             NOT NULL NUMBER
 CUST_GENDER                         NOT NULL CHAR(1)
 CUST_YEAR_OF_BIRTH                  NOT NULL NUMBER(4)
 
BEGIN
    dbms_data_mining_transform.CREATE_NORM_LIN(
       norm_table_name  => 'norm_tbl');
       dbms_data_mining_transform.INSERT_NORM_LIN_ZSCORE(
       norm_table_name  => 'norm_tbl',
       data_table_name  => 'mining_data',
       exclude_list     => dbms_data_mining_transform.COLUMN_LIST( 'cust_id'),
       round_num        => 3);
END;
/
 
SELECT col, shift, scale FROM norm_tbl;
 
COL                  SHIFT SCALE
-------------------- ----- -----
CUST_YEAR_OF_BIRTH    1960    15
 
DECLARE
    xforms      dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
    dbms_data_mining_transform.STACK_NORM_LIN (
        norm_table_name    => 'norm_tbl',
        xform_list        => xforms);
    dbms_data_mining_transform.XFORM_STACK (
        xform_list         => xforms,
        data_table_name    => 'mining_data',
        xform_view_name    => 'mining_data_stack');
END;
/
 
set long 3000
SQL> SELECT text FROM user_views WHERE view_name IN 'MINING_DATA_STACK';
 
TEXT
--------------------------------------------------------------------------------
SELECT "CUST_ID","CUST_GENDER",("CUST_YEAR_OF_BIRTH"-1960)/15 "CUST_YEAR_OF_BIRT
H" FROM mining_data

Syntax

DBMS_DATA_MINING_TRANSFORM.SET_EXPRESSION (
           expression    IN OUT NOCOPY EXPRESSION_REC,
           chunk                       VARCHAR2 DEFAULT NULL);

Parameters

Notes

1. You can pass NULL in the chunk argument to SET_EXPRESSION to clear the previous chunk. The default value of chunk is NULL.

2. See "About Transformation Lists".

3. See "Operational Notes".

Examples

In this example, two calls to SET_EXPRESSION construct a transformation expression and two calls construct the reverse transformation.

CREATE OR REPLACE VIEW mining_data AS
       SELECT cust_id, cust_year_of_birth, cust_postal_code, cust_credit_limit
       FROM sh.customers;
 
DECLARE
        v_expr dbms_data_mining_transform.EXPRESSION_REC;
        v_rexp dbms_data_mining_transform.EXPRESSION_REC;
        v_xrec dbms_data_mining_transform.TRANSFORM_REC;
        v_xlst dbms_data_mining_transform.TRANSFORM_LIST :=
                                dbms_data_mining_transform.TRANSFORM_LIST(NULL);
BEGIN
    dbms_data_mining_transform.SET_EXPRESSION(
         EXPRESSION  => v_expr,
         CHUNK       => '("CUST_YEAR_OF_BIRTH"-1910)');
    dbms_data_mining_transform.SET_EXPRESSION(
          EXPRESSION  => v_expr,
          CHUNK       => '/77');
    dbms_data_mining_transform.SET_EXPRESSION(
          EXPRESSION  => v_rexp,
          CHUNK       => '"CUST_YEAR_OF_BIRTH"*77');
    dbms_data_mining_transform.SET_EXPRESSION(
          EXPRESSION  => v_rexp,
          CHUNK       => '+1910');
 
    v_xrec := null;
    v_xrec.attribute_name := 'CUST_YEAR_OF_BIRTH';
    v_xrec.expression := v_expr;
    v_xrec.reverse_expression := v_rexp;
    v_xlst.TRIM;
    v_xlst.extend(1);
    v_xlst(1) := v_xrec;
 
    dbms_data_mining_transform.XFORM_STACK (
        xform_list           =>  v_xlst,
        data_table_name      => 'mining_data',
        xform_view_name      => 'v_xlst_view');
 
    dbms_output.put_line('====');
    FOR i IN 1..v_xlst.count LOOP
      dbms_output.put_line('ATTR: '||v_xlst(i).attribute_name);
      dbms_output.put_line('SUBN: '||v_xlst(i).attribute_subname);
      FOR j IN v_xlst(i).expression.lb..v_xlst(i).expression.ub LOOP
        dbms_output.put_line('EXPR: '||v_xlst(i).expression.lstmt(j));
      END LOOP;
      FOR j IN v_xlst(i).reverse_expression.lb..
                v_xlst(i).reverse_expression.ub LOOP
        dbms_output.put_line('REXP: '||v_xlst(i).reverse_expression.lstmt(j));
      END LOOP;
      dbms_output.put_line('====');
    END LOOP;
  END;
/
====
ATTR: CUST_YEAR_OF_BIRTH
SUBN:
EXPR: ("CUST_YEAR_OF_BIRTH"-1910)
EXPR: /77
REXP: "CUST_YEAR_OF_BIRTH"*77
REXP: +1910
====

Syntax

DBMS_DATA_MINING_TRANSFORM.SET_TRANSFORM (
          xform_list               IN OUT NOCOPY TRANSFORM_LIST,
          attribute_name           VARCHAR2,
          attribute_subname        VARCHAR2,
          expression               VARCHAR2,
          reverse_expression       VARCHAR2,
          attribute_spec           VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

1. See "Operational Notes". The following sections are especially relevant:

   • "About Transformation Lists"

   • "Nested Data Transformations"

2. As shown in the following example, you can eliminate an attribute by specifying a null transformation expression and reverse expression. You can also use the STACK interface to remove a column (CREATE_COL_REM Procedure and STACK_COL_REM Procedure).

Syntax

DBMS_DATA_MINING_TRANSFORM.STACK_BIN_CAT (
     bin_table_name     IN            VARCHAR2,
     xform_list         IN OUT NOCOPY TRANSFORM_LIST,
     literal_flag       IN            BOOLEAN  DEFAULT FALSE,
     bin_schema_name    IN            VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes". The following sections are especially relevant:

• "About Transformation Lists"

• "About Stacking"

• "Nested Data Transformations"

Examples

This example shows how a binning transformation for the categorical column cust_postal_code could be added to a stack called mining_data_stack.

CREATE or REPLACE VIEW mining_data AS
    SELECT cust_id, cust_postal_code, cust_credit_limit
       FROM sh.customers
       WHERE cust_id BETWEEN 100050 AND 100100;
BEGIN
   dbms_data_mining_transform.CREATE_BIN_CAT ('bin_cat_tbl');
   dbms_data_mining_transform.INSERT_BIN_CAT_FREQ (
        bin_table_name   => 'bin_cat_tbl',
        data_table_name  => 'mining_data',
        bin_num          =>  3);
  END;
/
DECLARE
  MINING_DATA_STACK   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
  dbms_data_mining_transform.STACK_BIN_CAT (
    bin_table_name       => 'bin_cat_tbl',
    xform_list           =>  mining_data_stack);
  dbms_data_mining_transform.XFORM_STACK (
    xform_list           =>  mining_data_stack,
    data_table_name      => 'mining_data',
    xform_view_name      => 'mining_data_stack_view');
  END;
/
-- Before transformation
column cust_postal_code format a16
SELECT * from mining_data 
              WHERE cust_id BETWEEN 100050 AND 100053
              ORDER BY cust_id;

  CUST_ID CUST_POSTAL_CODE CUST_CREDIT_LIMIT
---------- ---------------- -----------------
    100050 76486                         1500
    100051 73216                         9000
    100052 69499                         5000
    100053 45704                         7000

-- After transformation
SELECT * FROM mining_data_stack_view
              WHERE cust_id BETWEEN 100050 AND 100053
              ORDER BY cust_id;
 
  CUST_ID CUST_POSTAL_CODE CUST_CREDIT_LIMIT
---------- ---------------- -----------------
    100050 4                             1500
    100051 1                             9000
    100052 4                             5000
    100053 4                             7000

Syntax

DBMS_DATA_MINING_TRANSFORM.STACK_BIN_NUM (
     bin_table_name     IN             VARCHAR2,
     xform_list         IN OUT  NOCOPY TRANSFORM_LIST,
     literal_flag       IN             BOOLEAN  DEFAULT FALSE,
     bin_schema_name    IN             VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes". The following sections are especially relevant:

• "About Transformation Lists"

• "About Stacking"

• "Nested Data Transformations"

Examples

This example shows how a binning transformation for the numerical column cust_credit_limit could be added to a stack called mining_data_stack.

CREATE OR REPLACE VIEW mining_data AS
    SELECT cust_id, cust_postal_code, cust_credit_limit
      FROM sh.customers
      WHERE cust_id BETWEEN 100050 and 100100;
BEGIN
  dbms_data_mining_transform.create_bin_num ('bin_num_tbl');
  dbms_data_mining_transform.insert_bin_num_qtile (
  bin_table_name    => 'bin_num_tbl',
  data_table_name   => 'mining_data',
  bin_num                   => 5,
  exclude_list      =>  dbms_data_mining_transform.COLUMN_LIST('cust_id'));
END;
/
DECLARE
   MINING_DATA_STACK   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
   dbms_data_mining_transform.STACK_BIN_CAT (
      bin_table_name          => 'bin_num_tbl',
      xform_list         =>  mining_data_stack);
   dbms_data_mining_transform.XFORM_STACK (
      xform_list         =>  mining_data_stack,
      data_table_name   => 'mining_data',
      xform_view_name   => 'mining_data_stack_view');
END;
/
-- Before transformation
SELECT cust_id, cust_postal_code, ROUND(cust_credit_limit) FROM mining_data
   WHERE cust_id BETWEEN 100050 AND 100055
   ORDER BY cust_id;
CUST_ID   CUST_POSTAL_CODE   ROUND(CUST_CREDIT_LIMIT)
-------   -----------------  -------------------------
100050    76486                                 1500
100051    73216                                 9000 
100052    69499                                 5000
100053    45704                                 7000
100055    74673                                11000
100055    74673                                11000

-- After transformation
SELECT cust_id, cust_postal_code, ROUND(cust_credit_limit)
   FROM mining_data_stack_view
   WHERE cust_id BETWEEN 100050 AND 100055
   ORDER BY cust_id;
CUST_ID   CUST_POSTAL_CODE   ROUND(CUST_CREDIT_LIMITT)
-------   ----------------   -------------------------
100050    76486                                     
100051    73216                                   2
100052    69499                                   1
100053    45704                                   
100054    88021                                   3
100055    74673                                   3

Syntax

DBMS_DATA_MINING_TRANSFORM.STACK_CLIP (
          clip_table_name     IN            VARCHAR2,
          xform_list          IN OUT NOCOPY TRANSFORM_LIST,
          clip_schema_name    IN            VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes". The following sections are especially relevant:

• "About Transformation Lists"

• "About Stacking"

• "Nested Data Transformations"

Examples

This example shows how a clipping transformation for the numerical column cust_credit_limit could be added to a stack called mining_data_stack.

CREATE OR REPLACE VIEW mining_data AS
       SELECT cust_id, cust_postal_code, cust_credit_limit
       FROM sh.customers
       WHERE cust_id BETWEEN 100050 AND 100100;
BEGIN
   dbms_data_mining_transform.create_clip ('clip_tbl');
   dbms_data_mining_transform.insert_clip_winsor_tail (
       clip_table_name   => 'clip_tbl',
       data_table_name   => 'mining_data',
       tail_frac         => 0.25,
       exclude_list      => dbms_data_mining_transform.COLUMN_LIST('cust_id'));
END;
/
DECLARE
      MINING_DATA_STACK   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
      dbms_data_mining_transform.STACK_CLIP (
         clip_table_name     => 'clip_tbl',
         xform_list          =>  mining_data_stack);
      dbms_data_mining_transform.XFORM_STACK (
          xform_list        =>  mining_data_stack,
          data_table_name   => 'mining_data',
          xform_view_name   => 'mining_data_stack_view');
END;
/
-- Before transformation
SELECT cust_id, cust_postal_code, round(cust_credit_limit) 
  FROM mining_data
    WHERE cust_id BETWEEN 100050 AND 100054
    ORDER BY cust_id;
    
CUST_ID   CUST_POSTAL_CODE   ROUND(CUST_CREDIT_LIMIT)
-------   ----------------   ------------------------ 
100050    76486                                 1500 
100051    73216                                 9000 
100052    69499                                 5000 
100053    45704                                 7000 
100054    88021                                11000 
 
-- After transformation
SELECT cust_id, cust_postal_code, round(cust_credit_limit)  
  FROM mining_data_stack_view
    WHERE cust_id BETWEEN 100050 AND 100054
    ORDER BY cust_id;
    
CUST_ID   CUST_POSTAL_CODE   ROUND(CUST_CREDIT_LIMIT)
-------   ----------------   ------------------------
100050    76486                                 5000
100051    73216                                 9000
100052    69499                                 5000
100053    45704                                 7000
100054    88021                                11000

Syntax

DBMS_DATA_MINING_TRANSFORM.STACK_COL_REM (
     rem_table_name     IN            VARCHAR2,
     xform_list         IN OUT NOCOPY TRANSFORM_LIST,
     rem_schema_name    IN            VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes". The following sections are especially relevant:

• "About Transformation Lists"

• "About Stacking"

• "Nested Data Transformations"

Examples

This example shows how the column cust_credit_limit could be removed in a transformation list called mining_data_stack.

CREATE OR REPLACE VIEW mining_data AS
     SELECT cust_id, country_id, cust_postal_code, cust_credit_limit
        FROM sh.customers;
 
BEGIN
    dbms_data_mining_transform.create_col_rem ('rem_tbl');
END;
/

INSERT into rem_tbl VALUES (upper('cust_postal_code'), null);
 
DECLARE
  MINING_DATA_STACK   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
     dbms_data_mining_transform.stack_col_rem (
          rem_table_name     => 'rem_tbl',
          xform_list         =>  mining_data_stack);
      dbms_data_mining_transform.XFORM_STACK (
          xform_list         =>  mining_data_stack,
          data_table_name    => 'mining_data',
          xform_view_name    => 'mining_data_stack_view');
END;
/
 
SELECT *  FROM mining_data
  WHERE cust_id BETWEEN 100050 AND 100051
  ORDER BY cust_id;
 
CUST_ID   COUNTRY_ID   CUST_POSTAL_CODE   CUST_CREDIT_LIMIT
-------   ----------   ----------------   -----------------
100050         52773   76486                          1500
100051         52790   73216                          9000
 
SELECT *  FROM mining_data_stack_view
  WHERE cust_id BETWEEN 100050 AND 100051
  ORDER BY cust_id;
 
CUST_ID   COUNTRY_ID   CUST_CREDIT_LIMIT
-------   ----------   -----------------
100050         52773              1500
100051         52790              9000

Syntax

DBMS_DATA_MINING_TRANSFORM.STACK_MISS_CAT (
     miss_table_name     IN       VARCHAR2,
     xform_list          IN OUT   NOCOPY TRANSFORM_LIST,
     miss_schema_name    IN       VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes". The following sections are especially relevant:

• "About Transformation Lists"

• "About Stacking"

• "Nested Data Transformations"

Examples

This example shows how the missing values in the column cust_marital_status could be replaced with the mode in a transformation list called mining_data_stack.

CREATE OR REPLACE VIEW mining_data AS
      SELECT cust_id, country_id, cust_marital_status
         FROM sh.customers
         where cust_id BETWEEN 1 AND 10;
 
BEGIN
  dbms_data_mining_transform.create_miss_cat ('miss_cat_tbl');
  dbms_data_mining_transform.insert_miss_cat_mode ('miss_cat_tbl', 'mining_data');
END;
/
 
DECLARE
  MINING_DATA_STACK   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
     dbms_data_mining_transform.stack_miss_cat (
          miss_table_name   => 'miss_cat_tbl',
          xform_list        => mining_data_stack);
      dbms_data_mining_transform.XFORM_STACK (
          xform_list        =>  mining_data_stack,
          data_table_name   => 'mining_data',
          xform_view_name   => 'mining_data_stack_view');
END;
/
SELECT * FROM mining_data
  ORDER BY cust_id;
 
CUST_ID   COUNTRY_ID   CUST_MARITAL_STATUS
-------   ----------   --------------------
      1      52789
      2      52778
      3      52770
      4      52770
      5      52789
      6      52769     single
      7      52790     single
      8      52790     married
      9      52770     divorced
     10      52790     widow
 
SELECT * FROM mining_data_stack_view
   ORDER By cust_id;
 
CUST_ID   COUNTRY_ID   CUST_MARITAL_STATUS
-------   -----------  --------------------
      1       52789    single
      2       52778    single
      3       52770    single
      4       52770    single
      5       52789    single
      6       52769    single
      7       52790    single
      8       52790    married
      9       52770    divorced
     10       52790    widow

Syntax

DBMS_DATA_MINING_TRANSFORM.STACK_MISS_NUM (
     miss_table_name     IN       VARCHAR2,
     xform_list          IN OUT   NOCOPY TRANSFORM_LIST,
     miss_schema_name    IN       VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes". The following sections are especially relevant:

• "About Transformation Lists"

• "About Stacking"

• "Nested Data Transformations"

Examples

This example shows how the missing values in the column cust_credit_limit could be replaced with the mean in a transformation list called mining_data_stack.

describe mining_data
 Name                                                  Null?    Type
 ----------------------------------------------------- -------- -----
 CUST_ID                                               NOT NULL NUMBER
 CUST_CREDIT_LIMIT                                              NUMBER

BEGIN
   dbms_data_mining_transform.create_miss_num ('miss_num_tbl');
   dbms_data_mining_transform.insert_miss_num_mean ('miss_num_tbl','mining_data');
END;
/
SELECT * FROM miss_num_tbl;
 
COL                  ATT      VAL
-------------------- ----- ------
CUST_ID                       5.5
CUST_CREDIT_LIMIT          185.71
 
DECLARE
    MINING_DATA_STACK   dbms_data_mining_transform.TRANSFORM_LIST;
  BEGIN
    dbms_data_mining_transform.STACK_MISS_NUM (
          miss_table_name   => 'miss_num_tbl',
          xform_list        => mining_data_stack);
    dbms_data_mining_transform.XFORM_STACK (
          xform_list        =>  mining_data_stack,
          data_table_name   => 'mining_data',
          xform_view_name   => 'mining_data_stack_view');
END;
/
-- Before transformation
SELECT * FROM mining_data
  ORDER BY cust_id;
CUST_ID CUST_CREDIT_LIMIT
------- -----------------
      1               100
      2
      3               200
      4
      5               150
      6               400
      7               150
      8
      9               100
     10               200
 
-- After transformation
SELECT * FROM mining_data_stack_view
  ORDER BY cust_id;
CUST_ID CUST_CREDIT_LIMIT
------- -----------------
      1               100
      2            185.71
      3               200
      4            185.71
      5               150
      6               400
      7               150
      8            185.71
      9               100
     10               200

Syntax

DBMS_DATA_MINING_TRANSFORM.STACK_NORM_LIN (
     norm_table_name     IN       VARCHAR2,
     xform_list          IN OUT   NOCOPY TRANSFORM_LIST,
     norm_schema_name    IN       VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes". The following sections are especially relevant:

• "About Transformation Lists"

• "About Stacking"

• "Nested Data Transformations"

Examples

This example shows how the column cust_credit_limit could be normalized in a transformation list called mining_data_stack.

CREATE OR REPLACE VIEW mining_data AS
       SELECT cust_id, country_id, cust_postal_code, cust_credit_limit
          FROM sh.customers;
BEGIN
   dbms_data_mining_transform.create_norm_lin ('norm_lin_tbl');
   dbms_data_mining_transform.insert_norm_lin_minmax (
       norm_table_name   => 'norm_lin_tbl',
       data_table_name   => 'mining_data',
       exclude_list      =>  dbms_data_mining_transform.COLUMN_LIST('cust_id',
                                                             'country_id'));
END;
/
SELECT * FROM norm_lin_tbl;
COL                  ATT    SHIFT  SCALE
-------------------- ----- ------ ------
CUST_CREDIT_LIMIT            1500  13500

DECLARE
   MINING_DATA_STACK   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
   dbms_data_mining_transform.stack_norm_lin (
        norm_table_name   => 'norm_lin_tbl',
        xform_list        => mining_data_stack);
   dbms_data_mining_transform.XFORM_STACK (
        xform_list        =>  mining_data_stack,
        data_table_name   => 'mining_data',
        xform_view_name   => 'mining_data_stack_view');
END;
/
SELECT * FROM mining_data
  WHERE cust_id between 1 and 10
  ORDER BY cust_id;
CUST_ID COUNTRY_ID CUST_POSTAL_CODE     CUST_CREDIT_LIMIT
------- ---------- -------------------- -----------------
      1      52789 30828                             9000
      2      52778 86319                            10000
      3      52770 88666                             1500
      4      52770 87551                             1500
      5      52789 59200                             1500
      6      52769 77287                             1500
      7      52790 38763                             1500
      8      52790 58488                             3000
      9      52770 63033                             3000
     10      52790 52602                             3000
 
SELECT * FROM mining_data_stack_view
  WHERE cust_id between 1 and 10
  ORDER BY cust_id;
CUST_ID COUNTRY_ID CUST_POSTAL_CODE     CUST_CREDIT_LIMIT
------- ---------- -------------------- -----------------
      1      52789 30828                           .55556
      2      52778 86319                           .62963
      3      52770 88666                                0
      4      52770 87551                                0
      5      52789 59200                                0
      6      52769 77287                                0
      7      52790 38763                                0
      8      52790 58488                           .11111
      9      52770 63033                           .11111
     10      52790 52602                           .11111

Syntax

DBMS_DATA_MINING_TRANSFORM.XFORM_BIN_CAT (
     bin_table_name       IN VARCHAR2,
     data_table_name      IN VARCHAR2,
     xform_view_name      IN VARCHAR2,
     literal_flag         IN BOOLEAN DEFAULT FALSE,
     bin_schema_name      IN VARCHAR2 DEFAULT NULL,
     data_schema_name     IN VARCHAR2 DEFAULT NULL,
     xform_schema_name    IN VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes".

Examples

This example creates a view that bins the cust_postal_code column. The data source consists of three columns from sh.customer.

describe mining_data
 Name                                   Null?    Type
 -------------------------------------- -------- ------------------------
 CUST_ID                                NOT NULL NUMBER
 CUST_POSTAL_CODE                       NOT NULL VARCHAR2(10)
 CUST_CREDIT_LIMIT                               NUMBER
 
SELECT * FROM mining_data WHERE cust_id between 104066 and 104069;
 
   CUST_ID CUST_POSTAL_CODE     CUST_CREDIT_LIMIT                                                   
--------- -------------------- -----------------                                                   
    104066 69776                             7000                                                   
    104067 52602                             9000                                                   
    104068 55787                            11000                                                   
    104069 55977                             5000                                                   
 
BEGIN
  dbms_data_mining_transform.create_bin_cat(
     bin_table_name     => 'bin_cat_tbl');
  dbms_data_mining_transform.insert_bin_cat_freq(
     bin_table_name     => 'bin_cat_tbl',
     data_table_name    => 'mining_data',
     bin_num           => 10);
   dbms_data_mining_transform.xform_bin_cat(
     bin_table_name     => 'bin_cat_tbl',
     data_table_name    => 'mining_data',
     xform_view_name    => 'bin_cat_view');
END;
/
 
SELECT * FROM bin_cat_view WHERE cust_id between 104066 and 104069;
 
   CUST_ID CUST_POSTAL_CODE     CUST_CREDIT_LIMIT                                                   
---------- -------------------- -----------------                                                   
    104066 6                                 7000                                                   
    104067 11                                9000                                                   
    104068 3                                11000                                                   
    104069 11                                5000                                                   
 
SELECT text FROM user_views WHERE view_name IN 'BIN_CAT_VIEW';
 
TEXT                                                                                                
--------------------------------------------------------------------------------                    
SELECT "CUST_ID",DECODE("CUST_POSTAL_CODE",'38082','1','45704','9','48346','5','                    
55787','3','63736','2','67843','7','69776','6','72860','10','78558','4','80841',                    
'8',NULL,NULL,'11') "CUST_POSTAL_CODE","CUST_CREDIT_LIMIT" FROM mining_data                         

Syntax

DBMS_DATA_MINING_TRANSFORM.XFORM_BIN_NUM (
     bin_table_name     IN VARCHAR2,
     data_table_name    IN VARCHAR2,
     xform_view_name    IN VARCHAR2,
     literal_flag       IN BOOLEAN DEFAULT FALSE,
     bin_schema_name    IN VARCHAR2 DEFAULT NULL,
     data_schema_name   IN VARCHAR2 DEFAULT NULL,
     xform_schema_name  IN VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes".

Examples

This example creates a view that bins the cust_credit_limit column. The data source consists of three columns from sh.customer.

Syntax

DBMS_DATA_MINING_TRANSFORM.XFORM_CLIP (
    clip_table_name       IN VARCHAR2, 
    data_table_name       IN VARCHAR2,
    xform_view_name       IN VARCHAR2,
    clip_schema_name      IN VARCHAR2 DEFAULT NULL,
    data_schema_name      IN VARCHAR2,DEFAULT NULL,
    xform_schema_name     IN VARCHAR2,DEFAULT NULL);

Parameters

Examples

This example creates a view that clips the cust_credit_limit column. The data source consists of three columns from sh.customer.

describe mining_data
 Name                           Null?    Type
 ------------------------------ -------- -------------------------
 CUST_ID                        NOT NULL NUMBER
 CUST_POSTAL_CODE               NOT NULL VARCHAR2(10)
 CUST_CREDIT_LIMIT                        NUMBER
 
BEGIN
   dbms_data_mining_transform.create_clip(
      clip_table_name    => 'clip_tbl');
   dbms_data_mining_transform.insert_clip_trim_tail(
      clip_table_name   => 'clip_tbl',
      data_table_name   => 'mining_data',
      tail_frac         => 0.05,
      exclude_list      => dbms_data_mining_transform.COLUMN_LIST('cust_id'));
   dbms_data_mining_transform.xform_clip(
      clip_table_name     => 'clip_tbl',
      data_table_name    => 'mining_data',
      xform_view_name    => 'clip_view');
END;
/
describe clip_view
 Name                          Null?    Type
 ----------------------------- -------- --------------------------
 CUST_ID                       NOT NULL NUMBER
 CUST_POSTAL_CODE              NOT NULL VARCHAR2(10)
 CUST_CREDIT_LIMIT                      NUMBER
 
SELECT MIN(cust_credit_limit), MAX(cust_credit_limit) FROM mining_data;
 
MIN(CUST_CREDIT_LIMIT) MAX(CUST_CREDIT_LIMIT)
---------------------- ----------------------
                  1500                  15000
 
SELECT MIN(cust_credit_limit), MAX(cust_credit_limit) FROM clip_view;
 
MIN(CUST_CREDIT_LIMIT) MAX(CUST_CREDIT_LIMIT)
---------------------- ----------------------
                  1500                  11000
 
set long 2000
SELECT text FROM user_views WHERE view_name IN 'CLIP_VIEW';
 
TEXT
--------------------------------------------------------------------------------
SELECT "CUST_ID","CUST_POSTAL_CODE",CASE WHEN "CUST_CREDIT_LIMIT" < 1500 THEN NU
LL WHEN "CUST_CREDIT_LIMIT" > 11000 THEN NULL ELSE "CUST_CREDIT_LIMIT" END "CUST
_CREDIT_LIMIT" FROM mining_data

Syntax

DBMS_DATA_MINING_TRANSFORM.XFORM_COL_REM (
     rem_table_name     IN       VARCHAR2,
     data_table_name    IN       VARCHAR2,
     xform_view_name    IN       VARCHAR2,
     rem_schema_name    IN       VARCHAR2 DEFAULT NULL,
     data_schema_name   IN       VARCHAR2 DEFAULT NULL,
     xform_schema_name  IN       VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes".

Examples

This example creates a view that includes all but one column from the table customers in the current schema.

describe customers
 Name                                      Null?    Type
 ----------------------------------------- -------- ----------------------------
 CUST_ID                                   NOT NULL NUMBER
 CUST_MARITAL_STATUS                                VARCHAR2(20)
 OCCUPATION                                         VARCHAR2(21)
 AGE                                                NUMBER
 YRS_RESIDENCE                                      NUMBER

BEGIN
    DBMS_DATA_MINING_TRANSFORM.CREATE_COL_REM ('colrem_xtbl');
END;
 /
INSERT INTO colrem_xtbl VALUES('CUST_MARITAL_STATUS', null);

BEGIN
   DBMS_DATA_MINING_TRANSFORM.XFORM_COL_REM (
     rem_table_name        => 'colrem_xtbl',
     data_table_name       => 'customers',
     xform_view_name       => 'colrem_view');
END;
/
describe colrem_view

 Name                                      Null?    Type
 ----------------------------------------- -------- ----------------------------
 CUST_ID                                   NOT NULL NUMBER
 OCCUPATION                                         VARCHAR2(21)
 AGE                                                NUMBER
 YRS_RESIDENCE                                      NUMBER

Syntax

DBMS_DATA_MINING_TRANSFORM.XFORM_EXPR_NUM (
     expr_pattern       IN       VARCHAR2,
     data_table_name    IN       VARCHAR2,
     xform_view_name    IN       VARCHAR2,
     exclude_list       IN       COLUMN_LIST DEFAULT NULL,
     include_list       IN       COLUMN_LIST DEFAULT NULL,
     col_pattern        IN       VARCHAR2 DEFAULT ':col',
     data_schema_name   IN       VARCHAR2 DEFAULT NULL,
     xform_schema_name  IN       VARCHAR2 DEFAULT NULL);

Parameters

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Usage Notes

1. The XFORM_EXPR_NUM procedure constructs numeric transformation expressions from the specified expression pattern (expr_pattern) by replacing every occurrence of the specified column pattern (col_pattern) with an actual column name.

   XFORM_EXPR_NUM uses the SQL REPLACE function to construct the transformation expressions.

   REPLACE (expr_pattern,col_pattern,'"column_name"') || '"column_name"'
   

   If there is a column match, then the replacement is made in the transformation expression; if there is not a match, then the column is used without transformation.

   See:

   Oracle Database SQL Language Reference for information about the REPLACE function

2. Because of the include and exclude list parameters, the XFORM_EXPR_NUM and XFORM_EXPR_STR procedures allow you to easily specify individual columns for transformation within large data sets. The other XFORM_* procedures support an exclude list only. In these procedures, you must enumerate every column that you do not want to transform.

3. See "Operational Notes"

Examples

This example creates a view that transforms the data type of numeric columns.

describe customers
 Name                                Null?    Type
 ----------------------------------- -------- ------------------------
 CUST_ID                             NOT NULL NUMBER
 CUST_MARITAL_STATUS                          VARCHAR2(20)
 OCCUPATION                                   VARCHAR2(21)
 AGE                                          NUMBER
 YRS_RESIDENCE                                NUMBER

BEGIN
  DBMS_DATA_MINING_TRANSFORM.XFORM_EXPR_NUM(
    expr_pattern         => 'to_char(:col)',
    data_table_name      => 'customers',
    xform_view_name      => 'cust_nonum_view',
    exclude_list         => dbms_data_mining_transform.COLUMN_LIST( 'cust_id'),
    include_list         => null,
    col_pattern          => ':col');
END;
/
describe cust_nonum_view
 Name                                Null?    Type
 ----------------------------------- -------- ------------------------
 CUST_ID                             NOT NULL NUMBER
 CUST_MARITAL_STATUS                          VARCHAR2(20)
 OCCUPATION                                   VARCHAR2(21)
 AGE                                          VARCHAR2(40)
 YRS_RESIDENCE                                VARCHAR2(40)

Syntax

DBMS_DATA_MINING_TRANSFORM.XFORM_EXPR_STR (
     expr_pattern       IN       VARCHAR2,
     data_table_name    IN       VARCHAR2,
     xform_view_name    IN       VARCHAR2,
     exclude_list       IN       COLUMN_LIST DEFAULT NULL,
     include_list       IN       COLUMN_LIST DEFAULT NULL,
     col_pattern        IN       VARCHAR2 DEFAULT ':col',
     data_schema_name   IN       VARCHAR2 DEFAULT NULL,
     xform_schema_name  IN       VARCHAR2 DEFAULT NULL);

Parameters

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

dbms_data_mining_transform.COLUMN_LIST('col1','col2',
                                       ...'coln')

Usage Notes

1. The XFORM_EXPR_STR procedure constructs character transformation expressions from the specified expression pattern (expr_pattern) by replacing every occurrence of the specified column pattern (col_pattern) with an actual column name.

   XFORM_EXPR_STR uses the SQL REPLACE function to construct the transformation expressions.

   REPLACE (expr_pattern,col_pattern,'"column_name"') || '"column_name"'
   

   If there is a column match, then the replacement is made in the transformation expression; if there is not a match, then the column is used without transformation.

   See:

   Oracle Database SQL Language Reference for information about the REPLACE function

2. Because of the include and exclude list parameters, the XFORM_EXPR_STR and XFORM_EXPR_NUM procedures allow you to easily specify individual columns for transformation within large data sets. The other XFORM_* procedures support an exclude list only. In these procedures, you must enumerate every column that you do not want to transform.

3. See "Operational Notes"

Examples

This example creates a view that transforms character columns to upper case.

describe customers
 Name                                Null?    Type
 ----------------------------------- -------- ------------------------
 CUST_ID                             NOT NULL NUMBER
 CUST_MARITAL_STATUS                          VARCHAR2(20)
 OCCUPATION                                   VARCHAR2(21)
 AGE                                          NUMBER
 YRS_RESIDENCE                                NUMBER

SELECT cust_id,  cust_marital_status, occupation FROM customers
    WHERE   cust_id > 102995
    ORDER BY cust_id desc;
 
CUST_ID CUST_MARITAL_STATUS  OCCUPATION
------- -------------------- ---------------------
 103000 Divorc.              Cleric.
 102999 Married              Cleric.
 102998 Married              Exec.
 102997 Married              Exec.
 102996 NeverM               Other
 
BEGIN
  DBMS_DATA_MINING_TRANSFORM.XFORM_EXPR_STR(
       expr_pattern            => 'upper(:col)',
       data_table_name         => 'customers',
       xform_view_name         => 'cust_upcase_view');
END;
/
describe cust_upcase_view
 Name                          Null?    Type
 ----------------------------- -------- --------------------
 CUST_ID                       NOT NULL NUMBER
 CUST_MARITAL_STATUS                    VARCHAR2(20)
 OCCUPATION                             VARCHAR2(21)
 AGE                                    NUMBER
 YRS_RESIDENCE                          NUMBER
 
SELECT cust_id,  cust_marital_status, occupation FROM cust_upcase_view
   WHERE   cust_id > 102995
   ORDER BY cust_id desc;
 
CUST_ID CUST_MARITAL_STATUS  OCCUPATION
------- -------------------- ---------------------
 103000 DIVORC.              CLERIC.
 102999 MARRIED              CLERIC.
 102998 MARRIED              EXEC.
 102997 MARRIED              EXEC.
 102996 NEVERM               OTHER

Syntax

DBMS_DATA_MINING_TRANSFORM.XFORM_MISS_CAT (
    miss_table_name       IN VARCHAR2, 
    data_table_name       IN VARCHAR2,
    xform_view_name       IN VARCHAR2,
    miss_schema_name      IN VARCHAR2 DEFAULT NULL,
    data_schema_name      IN VARCHAR2 DEFAULT NULL,
    xform_schema_name     IN VARCHAR2 DEFAULT NULL;

Parameters

Usage Notes

See "Operational Notes".

Examples

This example creates a view that replaces missing categorical values with the mode.

SELECT * FROM geog;

REG_ID REGION
------ ------------------------------
     1 NE
     2 SW
     3 SE
     4 SW
     5
     6 NE
     7 NW
     8 NW
     9
    10
    11 SE
    12 SE
    13 NW
    14 SE
    15 SE
 
SELECT STATS_MODE(region) FROM geog;

STATS_MODE(REGION)
------------------------------
SE
 
BEGIN
  DBMS_DATA_MINING_TRANSFORM.CREATE_MISS_CAT('misscat_xtbl');
  DBMS_DATA_MINING_TRANSFORM.INSERT_MISS_CAT_MODE (
    miss_table_name         => 'misscat_xtbl',
    data_table_name         => 'geog' );
END;
/

SELECT col, val FROM misscat_xtbl;

COL        VAL
---------- ----------
REGION     SE
 
BEGIN
  DBMS_DATA_MINING_TRANSFORM.XFORM_MISS_CAT (
     miss_table_name        => 'misscat_xtbl',
     data_table_name        => 'geog',
     xform_view_name        => 'geogxf_view');
END;
/

SELECT * FROM geogxf_view;

REG_ID REGION
------ ------------------------------
     1 NE
     2 SW
     3 SE
     4 SW
     5 SE
     6 NE
     7 NW
     8 NW
     9 SE
    10 SE
    11 SE
    12 SE
    13 NW
    14 SE
    15 SE

Syntax

DBMS_DATA_MINING_TRANSFORM.XFORM_MISS_NUM (
    miss_table_name       IN VARCHAR2, 
    data_table_name       IN VARCHAR2,
    xform_view_name       IN VARCHAR2,
    miss_schema_name      IN VARCHAR2 DEFAULT NULL,
    data_schema_name      IN VARCHAR2 DEFAULT NULL,
    xform_schema_name     IN VARCHAR2 DEFAULT NULL;

Parameters

Usage Notes

See "Operational Notes".

Examples

This example creates a view that replaces missing numerical values with the mean.

SELECT * FROM items;
 
ITEM_ID       QTY
---------- ------
aa            200
bb            200
cc            250
dd
ee
ff            100
gg            250
hh            200
ii
jj            200
 
SELECT AVG(qty) FROM items;
 
AVG(QTY)
--------
     200
 
BEGIN
  DBMS_DATA_MINING_TRANSFORM.CREATE_MISS_NUM('missnum_xtbl');
  DBMS_DATA_MINING_TRANSFORM.INSERT_MISS_NUM_MEAN (
     miss_table_name          => 'missnum_xtbl',
     data_table_name         => 'items' );
END;
/
 
SELECT col, val FROM missnum_xtbl;
 
COL           VAL
---------- ------
QTY           200
 
BEGIN
    DBMS_DATA_MINING_TRANSFORM.XFORM_MISS_NUM (
        miss_table_name        => 'missnum_xtbl',
        data_table_name        => 'items',
        xform_view_name        => 'items_view');
END;
/
 
SELECT * FROM items_view;
 
ITEM_ID       QTY
---------- ------
aa            200
bb            200
cc            250
dd            200
ee            200
ff            100
gg            250
hh            200
ii            200
jj            200

Syntax

DBMS_DATA_MINING_TRANSFORM.XFORM_NORM_LIN (
     norm_table_name      IN VARCHAR2,
     data_table_name      IN VARCHAR2,
     xform_view_name      IN VARCHAR2,
     norm_schema_name     IN VARCHAR2 DEFAULT NULL,
     data_schema_name     IN VARCHAR2 DEFAULT NULL,
     xform_schema_name    IN VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes".

Examples

This example creates a view that normalizes the cust_year_of_birth and cust_credit_limit columns. The data source consists of three columns from sh.customer.

CREATE OR REPLACE VIEW mining_data AS
     SELECT cust_id, cust_year_of_birth, cust_credit_limit
     FROM sh.customers;

describe mining_data
 Name                                   Null?    Type
 -------------------------------------- -------- --------------------------
 CUST_ID                                NOT NULL NUMBER
 CUST_YEAR_OF_BIRTH                     NOT NULL NUMBER(4)
 CUST_CREDIT_LIMIT                               NUMBER
 
SELECT * FROM mining_data WHERE cust_id > 104495
        ORDER BY cust_year_of_birth;
 
 CUST_ID CUST_YEAR_OF_BIRTH CUST_CREDIT_LIMIT
-------- ------------------ -----------------
  104496               1947              3000
  104498               1954             10000
  104500               1962             15000
  104499               1970              3000
  104497               1976              3000
 
BEGIN
  dbms_data_mining_transform.CREATE_NORM_LIN(
       norm_table_name            => 'normx_tbl');
 dbms_data_mining_transform.INSERT_NORM_LIN_MINMAX(
      norm_table_name      => 'normx_tbl',
      data_table_name      => 'mining_data',
      exclude_list        => dbms_data_mining_transform.COLUMN_LIST( 'cust_id'),
      round_num   => 3);
END;
/
 
SELECT col, shift, scale FROM normx_tbl;
 
COL                               SHIFT    SCALE                           
------------------------------ -------- --------                           
CUST_YEAR_OF_BIRTH                 1910       77                           
CUST_CREDIT_LIMIT                  1500    13500                           
 
BEGIN
  DBMS_DATA_MINING_TRANSFORM.XFORM_NORM_LIN (
     norm_table_name       => 'normx_tbl',
     data_table_name       => 'mining_data',
     xform_view_name       => 'norm_view');
END;
/
 
SELECT * FROM norm_view WHERE cust_id > 104495
        ORDER BY cust_year_of_birth;
 
 CUST_ID CUST_YEAR_OF_BIRTH CUST_CREDIT_LIMIT
-------- ------------------ -----------------
  104496           .4805195          .1111111
  104498           .5714286          .6296296
  104500           .6753247                 1
  104499           .7792208          .1111111
  104497           .8571429          .1111111
 
 
set long 2000
SQL> SELECT text FROM user_views WHERE view_name IN 'NORM_VIEW';
 
TEXT                                                                       
---------------------------------------------------------------------------
SELECT "CUST_ID",("CUST_YEAR_OF_BIRTH"-1910)/77 "CUST_YEAR_OF_BIRTH",("CUST
_CREDIT_LIMIT"-1500)/13500 "CUST_CREDIT_LIMIT" FROM mining_data            
                                                                           

Syntax

DBMS_DATA_MINING_TRANSFORM.XFORM_STACK (
     xform_list         IN     TRANSFORM_list,
     data_table_name    IN     VARCHAR2,
     xform_view_name    IN     VARCHAR2,
     data_schema_name   IN     VARCHAR2 DEFAULT NULL,
     xform_schema_name  IN     VARCHAR2 DEFAULT NULL);

Parameters

Usage Notes

See "Operational Notes". The following sections are especially relevant:

• "About Transformation Lists"

• "About Stacking"

• "Nested Data Transformations"

Examples

This example applies a transformation list to the view dmuser.cust_info and shows how the data is transformed.The CREATE statement for cust_info is shown in "DESCRIBE_STACK Procedure".

BEGIN
  dbms_data_mining_transform.CREATE_BIN_NUM ('birth_yr_bins');
  dbms_data_mining_transform.INSERT_BIN_NUM_QTILE (
        bin_table_name   => 'birth_yr_bins',
        data_table_name  =>  'cust_info',
        bin_num          =>   6,
        exclude_list     =>  dbms_data_mining_transform.column_list(
                                 'cust_id','country_id'));
END;
/
SELECT * FROM birth_yr_bins;

COL                  ATT      VAL BIN
-------------------- ----- ------ ----------
CUST_YEAR_OF_BIRTH           1922
CUST_YEAR_OF_BIRTH           1951 1
CUST_YEAR_OF_BIRTH           1959 2
CUST_YEAR_OF_BIRTH           1966 3
CUST_YEAR_OF_BIRTH           1973 4
CUST_YEAR_OF_BIRTH           1979 5
CUST_YEAR_OF_BIRTH           1986 6

DECLARE
      cust_stack   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
      dbms_data_mining_transform.SET_TRANSFORM (cust_stack,
          'country_id', NULL, 'country_id/10', 'country_id*10');
      dbms_data_mining_transform.STACK_BIN_NUM ('birth_yr_bins',
          cust_stack);
      dbms_data_mining_transform.SET_TRANSFORM (cust_stack,
          'custprods', 'Mouse Pad', 'value*100', 'value/100');
      dbms_data_mining_transform.XFORM_STACK(
          xform_list        => cust_stack,
          data_table_name   => 'cust_info',
          xform_view_name   =>  'cust_xform_view');
  END;
/

-- Two rows of data without transformations
SELECT * from cust_info WHERE cust_id BETWEEN 100010 AND 100011;

CUST_ID COUNTRY_ID CUST_YEAR_OF_BIRTH CUSTPRODS(ATTRIBUTE_NAME, VALUE)
------- ---------- ------------------ -----------------------------------------
 100010      52790               1975 DM_NESTED_NUMERICALS(
                                        DM_NESTED_NUMERICAL(
                                         '18" Flat Panel Graphics Monitor', 1),
                                        DM_NESTED_NUMERICAL(
                                         'SIMM- 16MB PCMCIAII card', 1))
 100011      52775               1972 DM_NESTED_NUMERICALS(
                                       DM_NESTED_NUMERICAL(
                                         'External 8X CD-ROM', 1),
                                       DM_NESTED_NUMERICAL(
                                         'Mouse Pad', 1),
                                       DM_NESTED_NUMERICAL(
                                        'SIMM- 16MB PCMCIAII card', 1),
                                       DM_NESTED_NUMERICAL(
                                         'Keyboard Wrist Rest', 1),
                                       DM_NESTED_NUMERICAL(
                                         '18" Flat Panel Graphics Monitor', 1),
                                       DM_NESTED_NUMERICAL(
                                         'O/S Documentation Set - English', 1))

-- Same two rows of data with transformations
SELECT * FROM cust_xform_view WHERE cust_id BETWEEN 100010 AND 100011;
 
CUST_ID  COUNTRY_ID  C  CUSTPRODS(ATTRIBUTE_NAME, VALUE)
-------  ----------  -  --------------------------------------------------------
 100010       5279   5  DM_NESTED_NUMERICALS(
                          DM_NESTED_NUMERICAL(
                           '18" Flat Panel Graphics Monitor', 1),
                          DM_NESTED_NUMERICAL(
                            'SIMM- 16MB PCMCIAII card', 1))
 100011     5277.5   4  DM_NESTED_NUMERICALS(
                          DM_NESTED_NUMERICAL(
                            'External 8X CD-ROM', 1),
                          DM_NESTED_NUMERICAL(
                            'Mouse Pad', 100),
                          DM_NESTED_NUMERICAL(
                            'SIMM- 16MB PCMCIAII card', 1),
                          DM_NESTED_NUMERICAL(
                            'Keyboard Wrist Rest', 1),
                          DM_NESTED_NUMERICAL(
                            '18" Flat Panel Graphics Monitor', 1),
                          DM_NESTED_NUMERICAL(
                            'O/S Documentation Set - English', 1))